COMP 150: Developmental Robotics Instructor: Jivko Sinapov - - PowerPoint PPT Presentation

▶
comp 150 developmental robotics
SMART_READER_LITE
LIVE PREVIEW

COMP 150: Developmental Robotics Instructor: Jivko Sinapov - - PowerPoint PPT Presentation

Feb 07, 2023 157 likes •604 views

COMP 150: Developmental Robotics Instructor: Jivko Sinapov www.cs.tufts.edu/~jsinapov This Week Embodiment Team-up Activity Literature Surveys Announcement Readings for Week 4 are out Homework 2 will go out on Thursday

slide-1
SLIDE 1

COMP 150: Developmental Robotics

Instructor: Jivko Sinapov www.cs.tufts.edu/~jsinapov

slide-2
SLIDE 2

This Week

  • Embodiment
  • Team-up Activity
  • Literature Surveys
slide-3
SLIDE 3

Announcement

  • Readings for Week 4 are out
  • Homework 2 will go out on Thursday
slide-4
SLIDE 4

Embodiment

No body Body

slide-5
SLIDE 5

Traditional View of AI

Mainstream Science on Intelligence December 13, 1994: An Editorial With 52 Signatories, History, and Bibliography by Linda S. Gottfredson, University of Delaware

“Intelligence is a very general mental capability that, among other things, involves the ability to reason, plan, solve problems, think abstractly, comprehend complex ideas, learn quickly and learn from experience.”

slide-6
SLIDE 6

Origin of Intelligence in Humans

slide-7
SLIDE 7

Leonardo da Vinci

[http://www.pc.rhul.ac.uk/staff/j.zanker/teach/ps2080/l4/ps2080_4.htm]

slide-8
SLIDE 8

Rene Descartes

[http://psych.hanover.edu/classes/neuropsychology/webnotes/Class2.html]

slide-9
SLIDE 9

Rene Descartes

slide-10
SLIDE 10

Rene Descartes

slide-11
SLIDE 11

Rene Descartes

slide-12
SLIDE 12

Homunculus

“A miniature, fully formed individual believed by adherents of the early biological theory of preformation to be present in the sperm cell.”

slide-13
SLIDE 13

Grown-up Homunculus

slide-14
SLIDE 14

Homunculus

[http://theboundsofcognition.blogspot.com/2010/12/gibsons-rejection-of-retinal-image-1.html]

slide-15
SLIDE 15

Avatars

slide-16
SLIDE 16

The Matrix

slide-17
SLIDE 17

[http://www.coolest-gadgets.com/20060402/top-10-best-april-fool%E2%80%99s-gadget-stories-and-hoaxes/]

Apps for the brain?

slide-18
SLIDE 18

Embodiment Principle

“An important implication of the verification principle is that the robot must have the ability to verify everything that it learns. Because verification cannot be performed in the absence

  • f actions the robot must have some means of

affecting the world, i.e., it must have a body.”

slide-19
SLIDE 19

Traditional vs Embodied AI

  • Abstract intelligence

– attempt to simulate

“highest” human faculties:

  • language, discursive

reason, mathematics, abstract problem solving

  • Environment model

– Condition for problem

solving in abstract way

– “brain in a vat”

  • Embodiment

– knowledge is implicit in the

fact that we have a body

  • embodiment is a foundation

for brain development

  • Intelligence develops

through interaction with environment

– Situated in a specific

environment

– Environment is its best

model

slide-20
SLIDE 20

Embodied AI

Embodied Intelligence (EI) is a mechanism that learns how to survive in a environment (potentially hostile)

  • Mechanism: biological, mechanical or virtual agent

with embodied sensors and actuators

  • EI acts on environment and perceives its actions
  • EI learns so it must have associative self-organizing memory
  • Knowledge is acquired by EI
slide-21
SLIDE 21

Embodied AI

Agent

Drawing by Ciarán O’Leary- Dublin Institute of Technology

slide-22
SLIDE 22

Embodied AI

Environment Environment Intelligence core Embodiment

Sensors Actuators

“Embodiment of a mind is a mechanism under the control of the intelligence core that contains sensors and actuators connected to the core through communication channels.”

Drawing and quote by Janusz Starzyk EECS, Ohio University

slide-23
SLIDE 23

Embodied AI

INPUT OUTPUT Simulation or Real-World System

Task Environment Agent Architecture

Long-term Memory

Short-term Memory

Reason Act

Perceive

RETRIEVAL LEARNING

From Randolph M. Jones, P : www.soartech.com

slide-24
SLIDE 24

Embodiment in Humans

slide-25
SLIDE 25

Embodiment in Humans

https://anagnk.files.wordpress.com/2013/03/fetal-growth.jpg

slide-26
SLIDE 26

Embodiment in Humans

Source: Getty Images

slide-27
SLIDE 27

Embodiment in Humans

slide-28
SLIDE 28

Embodiment in Humans

Human Brain Human Brain at Birth at Birth 6 Years Old 6 Years Old 14 Years Old 14 Years Old

Rethinking the Brain, Families and Work Institute, Rima Shore, 1997.

slide-29
SLIDE 29

Synaptic Density over Time

Thompson, R. A., & Nelson, C. A. (2001). Developmental science and the media: Early brain development. American Psychologist, 56(1), 5-15.

slide-30
SLIDE 30

Penfield (a.k.a. Sensory) Homunculus

slide-31
SLIDE 31

And its 3D analog

slide-32
SLIDE 32

Sensory and Motor Homuculus

https://www.ebmconsult.com/content/images/Anatomy/Homonculus%20Sensory%20and%20Motor%20Cortex%20v2.png

slide-33
SLIDE 33

Discussion

  • Do we really need a body to study AI?
  • What are some of the differences in practice

between embodied AI and disembodied AI?

  • Which one is ``harder’’ to do?
slide-34
SLIDE 34
slide-35
SLIDE 35

How do robots currently represent their own bodies?

slide-36
SLIDE 36

What kind of data structure would you define to represent this:

http://nptel.ac.in/courses/112103174/module7/lec5/images/e1.jpg

slide-37
SLIDE 37

What about this?

slide-38
SLIDE 38

Types of Robot Joints

http://nptel.ac.in/courses/112103174/module7/lec5/images/01.png

slide-39
SLIDE 39

Robot Bodies in ROS

slide-40
SLIDE 40

ROS Tutorial on URDF

http://wiki.ros.org/urdf/Tutorials

slide-41
SLIDE 41

What are some limitations of this approach to represent bodies?

slide-42
SLIDE 42

Team-up Activity

slide-43
SLIDE 43