INTRODUCTION AUTONOMOUS SYSTEMS LECTURE NOTES

Autonomous Systems 2024© Pedro Lima Introduction
AUTONOMOUS SYSTEMS
Pedro U. Lima
Instituto Superior Técnico/Instituto de Sistemas e Robótica
April 2024
Course Handouts
All rights reserved
INTRODUCTION

Autonomous Systems
What is an Autonomous System?
2

Autonomous Systems
3
AUTONOMY
From Greek αυτονομία autonomia,
noun of quality from αυτόνομος autonomos “independent,
living by one’s own laws”,
from αυτο auto- “self” + νόμος nomos “custom, law”.
In Wikipedia

Autonomous Systems
4
SYSTEM
From late Latin systēma, from Ancient Greek σύστημα
(sustēma), “organised whole, body”),
from σύν (sun), “with, together”) + ἵστημι (histēmi), “I stand”).
A collection of organized things.
A way of organizing or planning.
A whole composed of relationships among the members.
In Wikipedia

Autonomous Systems
5
AUTONOMOUS SYSTEM
A collection of organized things, composed of relationships
among them, and capable of living independently by its own
laws

Autonomous Systems
6
AUTONOMOUS AGENT
An agent is anything that can be viewed as perceiving its
environment through sensors and acting upon that
environment through effectors (Russel & Norvig, 1995).
Jennings and Wooldridge have three key concepts for an
agent:
• situatedness,
• autonomy,
• flexibility

Autonomous Systems 2024© Pedro Lima Introduction 8
AUTONOMOUS AGENTS
• should be able to learn from experience
• should be able to interact and even cooperate with other
autonomous agents
• should have means of handling the uncertainty associated to its
sensor inputs and the effects of its actions over a surrounding ,
possibly dynamic, environment
• should have means to take rational decisions, leading to some
goal
Autonomous Systems

Autonomous Systems
AUTONOMOUS ROBOTS
Autonomous robots are robots (embodied situated agents)
which can perform desired tasks in unstructured
environments without continuous human guidance. Many
kinds of robots have some degree of autonomy. Different
robots can be autonomous in different ways.
In Wikipedia

Autonomous Systems
AUTONOMOUS ROBOTS have the ability to
• Gain information about the environment.
• Work for an extended period without human intervention.
• Move either all or part of itself throughout its operating
environment without human assistance.
• Avoid situations that are harmful to people, property, or itself.
• An autonomous robot may also learn or gain new
capabilities like adjusting strategies for accomplishing its
task(s) or adapting to changing surroundings.
In Wikipedia

Artificial Intelligence vs Intelligent Robotics

Advanced Robots

1950
1970-2
1977 1997
1989
1997
1998
1993
2002
2001
2003
Autonomous Mobile Robots – Historical Evolution
2008
2010
2004
2014
2012
2016
1996
2011
2018
2022

Grey Walter (UK, University of Bristol) built
three wheeled, turtle like, mobile robotic vehicles.
These vehicles had:
a light sensor,
touch sensor,
propulsion motor,
steering motor, and a two vacuum tube
analog computer.
Even with this simple design, Grey demonstrated
that his turtles exhibited complex behaviors. He
called his turtles Machina Speculatrix after their
speculative tendency to explore their environment.
The Adam and Eve of his robots were named
Elmer and Elsie ( ELectro MEchanical Robots,
Light Sensitive. )
1950
http://en.wikipedia.org/wiki/William_Grey_Walter
Elsie
14

Shakey (Stanford University)
was the first mobile robot to be
controlled by vision
1969
Shakey was set (relatively) simple
tasks to solve:
• To recognize an object using vision
• Find its way to the object
• Perfom some action on the object
(for example, to push it over)
15
See a recent talk on Shakey at ICRA
2015 by Peter Hart:
https://youtu.be/t6B9wpMyKyc?si=TnZ9CmMePLdCD9c4

AGV, Efacec – Transformers factory LGV, Soporcel Paper factory
Autonomous Mobile Robots – Industrial (1)
AGVs and LGVs

Mobile Manipulators
KUKA YouBot MetraLabs SCITOS G5
with Schunk arm

KIVA Systems / Amazon

BAXTER / Rethink Robotics
BAXTER

Autonomous Mobile Robots – Indoors

Autonomous Mobile Robots – Field

Infante – ISR/IST, Portugal
Helicopter
AIR
UNDERWATER OCEAN
Delfim – ISR/IST, Portugal
Autonomous Mobile Robots – Aerial and Marine
Quadcopters, Hexacopters, Octocopters

Mercedes Driverless Car
Autonomous Mobile Robots – Autonomous Cars (1)
Reprinted from IEEE Spectrum, July 2014

Mercedes Driverless Car
Autonomous Mobile Robots – Autonomous Cars (2)
Reprinted from IEEE Spectrum, July 2014

Autonomous Mobile Robots – Legged (1)
Atlas, Boston Dynamics

Autonomous Mobile Robots – Legged (2)
Quadrupede, Boston Dynamics

Spacecraft Formations
27

Robot Networks
28

Multi Robot Cooperative Systems
Soccer Robots

Robots + Sensor Networks in Hospitals (1)
• Goal: Symbiotic Interaction with Autistic Children
• Case study: Hospital Garcia da Orta pilot sessions
CMU-Portugal INSIDE project
One way mirror
Set of 3D cameras
Plastic toys
Tablet with
virtual puzzle
LCD for
facial expressions
ASTRO ROBOT
Touchscreen with
virtual Tangram
Pouch with
RFID sensors
HD camera
Local camera
processing
Microphone for
therapist
INESC-ID + ISR/IST

CMU-Portugal INSIDE project
INESC-ID + ISR/IST

FP7 MOnarCH (Multi-Robot Cognitive Systems Operating in Hospitals)
(Coordinated by ISR/IST)

MBOT / “Gasparzinho” Evolution
IDMind + ISR/IST

MBOT (1)
Touch Screen
Video Projector
LEDs Face Expression
Interaction Kinect Camera
with microphones
Laser range finder
Navigation
Asus Xtion camera
Servo motors
shoulders and head

Body Touch
Capacitive cells
Voice and Sounds
LEDs “emotional” state
LEDs robot state
RFID reader
MBOT (2)

Autonomous Systems – Non-Robotic Systems
36
1996: IBM Deep Blue computer defeats chess
world champion Garry Kasparov
2011
2011: IBM Watson defeats JEOPARDY former
winners Brad Rutter and Ken Jennings
2016: Google Deep Mind AlphaGo defeats GO
world champion Lee Sedol

End2End Approaches
37
Machine Learning
e.g., Large Language Model
plan
plan

Autonomous Networked Robot Systems
ISR/IST SocRob@Home

• Growing robots, inspired in humans cognition
• Bio-inspired robot collectives
• Robot societies using social sciences concepts
…
Autonomous Systems – New Challenges

40
• Autonomous cars ethical dilemmas
• Threats to employment:
• companies should pay for redeployment or training of replaced
workers
• or taxes should be charged to companies which strongly invest on
automation
• …
Automation can bring several advantages to society,
including more wealth:
the issue is to make sure it is distributed by all, not just a few
Autonomous Systems – Ethical Challenges

Components of an Autonomous System
An autonomous system (AS) is a combination of various physical
(hardware) and computational (software) subsystems:
– Acting and Moving – how does an AS actuate over its environment
– Sensing – how does an AS measure properties of itself (e.g., its
location) and of its environment
– Reasoning and Planning – how does na AS map the measurements
into actions, possibly planning short- and long-term actions and motions
– Communication – how does a robot communicate with an outside
operator and with other robots; how does it interact naturally with
humans?
Classical cycle: SENSING – PROCESSING - ACTING
41

INTRODUCTION AUTONOMOUS SYSTEMS LECTURE NOTES

More Related Content

What's hot

Similar to INTRODUCTION AUTONOMOUS SYSTEMS LECTURE NOTES

Recently uploaded

INTRODUCTION AUTONOMOUS SYSTEMS LECTURE NOTES