Robo sapiens The Forefront of AI? CPSC 433 Christian Jacob Dept. - - PowerPoint PPT Presentation

▶
robo sapiens the forefront of ai
SMART_READER_LITE
LIVE PREVIEW

Robo sapiens The Forefront of AI? CPSC 433 Christian Jacob Dept. - - PowerPoint PPT Presentation

Aug 15, 2022 587 likes •1.04k views

Robo sapiens The Forefront of AI? CPSC 433 Christian Jacob Dept. of Computer Science Dept. of Biochemistry & Molecular Biology University of Calgary Christian Jacob, University of Calgary CPSC 433 Arti fi cial Intelligence: An

slide-1
SLIDE 1

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

CPSC 433 Christian Jacob

  • Dept. of Computer Science
  • Dept. of Biochemistry & Molecular Biology

University of Calgary

Robo sapiens The Forefront of AI?

slide-2
SLIDE 2

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Robo sapiens

slide-3
SLIDE 3

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Challenges

  • f the Physical W
  • rld

The physical world we live in is very demanding — especially for robots.

  • Inaccessibility
  • Artificial sensors are still imperfect (or too perfect).
  • Nondeterminism
  • A robot needs to deal with uncertainty.
slide-4
SLIDE 4

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Challenges

  • f the Physical W
  • rld (2)
  • Non-episodicity
  • Effects of an action change over time.
  • Dynamics
  • Robots need to decide when to ‘think’ and when to

act immediately.

  • Continuity
  • States and actions are drawn from a continuum of

physical configurations and motions.

slide-5
SLIDE 5

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

What are Robots Good For?

slide-6
SLIDE 6

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

  • Fine-motion (bounded-error) planning
  • Assumes bounds on sensor and actuator uncertainty.
  • Partial knowledge of the environment is known to the

system.

  • Most of the planning is done offline.
  • Used for planning small, precise motions of assembly

robots.

Motion Planning

slide-7
SLIDE 7

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Assembly Robot

Fine-Motion Planning

slide-8
SLIDE 8

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Manufacturing and Materials Handling

slide-9
SLIDE 9

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

  • Cell / map decomposition
  • Break continuous space into a finite number of

discrete search problems.

  • Skeletonization
  • Compute a uni-directional ‘skeleton’ (subset) of the

configuration space (==> graph search problem)

Navigation

slide-10
SLIDE 10

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

  • Landmark-based navigation
  • This method assumes that some regions exist in

which the robot location can be pinpointed using landmarks.

  • Outside those regions there may only be orientation

information.

Navigation & Motion Planning

slide-11
SLIDE 11

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Landmark Navigation

slide-12
SLIDE 12

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Gofer Service Robots

Bell & Howell Mail Mobile

slide-13
SLIDE 13

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

  • Online Algorithms
  • The robot makes decisions at run time (no need for
  • ffline planning).
  • This method assumes that the environment is

completely unknown, and has to be ‘explored’.

  • The robot is usually equipped with a position sensor

and knows the location of its goal.

Navigation & Motion Planning

slide-14
SLIDE 14

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Exploration

Nomad (Carnegie Mellon University)

slide-15
SLIDE 15

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Nomad (CMU, 1997)

Exploration

Text

http://www-2.cs.cmu.edu/~lri/nav97.html

slide-16
SLIDE 16

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Mars Pathfinder Sojourner Mars Pathfinder Sojourner

Online Algorithm

Rover Mars Mission 2004

slide-17
SLIDE 17

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

More Robot Examples

Useful and curious ...

slide-18
SLIDE 18

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Lunokhod Moon Robot

Hazardous Environments

slide-19
SLIDE 19

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Dante II Frame W alking Robot

Hazardous Environments

slide-20
SLIDE 20

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Wheelbarrow: Bomb Disposal Robot

Telepresence

slide-21
SLIDE 21

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Advanced Tethered V ehicl

Telepresence

slide-22
SLIDE 22

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

ARTEMIS: Advanced Robot & Telemanipulator System for Minimal Invasive Surgery

Telepresence

slide-23
SLIDE 23

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Sigourney W eaver in the movie Aliens

Augmentation of Human Abilities

slide-24
SLIDE 24

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Augmentation of Human Abilities

slide-25
SLIDE 25

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

  • Effectors: tools for action
  • Locomotion
  • Manipulation

What Makes Robots W

  • rk?
slide-26
SLIDE 26

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

  • Sensors: tools for perception
  • Proprioception
  • Force sensing
  • Tactile sensing
  • ...

What Makes Robots W

  • rk?
slide-27
SLIDE 27

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

MIT’s 3D Hopper (1984)

Locomotion

http://www.computerthai.or.th/Technology/MIT robots/mit_robots.html

slide-28
SLIDE 28

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Spring Flamingo (MIT)

Proprioception

http://www.computerthai.or.th/Technology/MIT robots/mit_robots.html

slide-29
SLIDE 29

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Spring Flamingo (MIT, 1996-2000)

Proprioception

http://www.computerthai.or.th/Technology/MIT robots/mit_robots.html

slide-30
SLIDE 30

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Proprioception

M2, Bipedal W alker (MIT, 2001-present)

http://www.computerthai.or.th/Technology/MIT robots/mit_robots.html

slide-31
SLIDE 31

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

MIT T

  • uch Lab

Haptics

slide-32
SLIDE 32

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

  • Sensors: tools for perception
  • Proprioception
  • Force sensing
  • Tactile sensing
  • Sonar
  • Camera, visual perception

What Makes Robots W

  • rk?
slide-33
SLIDE 33

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Peoplebots (ActivMedia)

Sonar Sensors

slide-34
SLIDE 34

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Fast Eye Gimbals (MIT)

Camera Sensors

slide-35
SLIDE 35

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

MIT

Kisme

slide-36
SLIDE 36

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Robots in our “Daily Lives”

slide-37
SLIDE 37

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

LOGO Robot

Seymour Papert

slide-38
SLIDE 38

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

AIBO (Sony) and RoboCup

Robot Teams

slide-39
SLIDE 39

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Ichiro Kato, W aseda University, Tokyo (1980-84)

W ABOT-2: Organ Player

In 1984, Waseda University presented the Wabot-2. This machine was the first attemps of specializing a robot in domestic use. The chosen activity was music, and the Wabot-2 got worldwide famous as the first robot in the world which played piano.

http://cdecas.free.fr/robots/wabot.php

slide-40
SLIDE 40

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

slide-41
SLIDE 41

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

V acuum Robot

Roomba Robotic Floor V ac

slide-42
SLIDE 42

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

Lawn Mowing ...

Friendly Robotics: Robomow

slide-43
SLIDE 43

CPSC 433 — Artificial Intelligence: An Introduction Christian Jacob, University of Calgary

  • Menzel, P

., and D’Alusio, F. (2000). Robo sapiens — Evolution of a New Species. Cambridge, MA, MIT Press.

  • Kurzweil, R. (1990). The Age of Inteigen
  • Machines. Cambridge, MA, MIT Press.

References