artificial life

48
Artificial life Based on Luc Steels (1995)

Upload: bobby

Post on 01-Feb-2016

31 views

Category:

Documents


0 download

DESCRIPTION

Artificial life. Based on Luc Steels (1995). Subject. Study : research and synthesis towards the artificial life domain Context : limits of system expert growth of computer power cognition approach. Start point. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Artificial life

Artificial life

Based on Luc Steels (1995)

Page 2: Artificial life

2

Subject

• Study : research and synthesis towards the artificial life domain

• Context : limits of system expert growth of computer power cognition approach

Page 3: Artificial life

3

Start point

• Scientific article :

« The Homo Cyber Sapiens, the Robot Homonidus Intelligens, and the ‘artificial life’ approach to artificial intelligence »

Luc Steels (1995)

Page 4: Artificial life

4

Luc Steels

• Specialized in the domain of artificial intelligence and artificial life applied to robot architectures and to the study of language

Fig 1. Luc Steels

Page 5: Artificial life

5

Luc Steels’ background

• Studied computer science at MIT (Massachusetts Institute of Technology – USA)

• Director of Sony Computer Science Laboratory in Paris

• Professor computer science at the University of Brussels

• Founded the VUB AI Laboratory (1983)

• Reviewer at CNRS

Page 6: Artificial life

6

Once upon a time…

evolutionAfter us ?UsHomo

SapiensHomo

Erectus

?Bionic man

Intelligentsystems

Artificial life

Page 7: Artificial life

7

Axes of discussion

• Bionic man or Homo cyber sapiens

• Intelligent systems or Robot Homonidus Intelligens

• Artificial life

Page 8: Artificial life

Artificial Life

Bionic manor Homo Cyber Sapiens

Page 9: Artificial life

9

Homo Cyber Sapiens

• Intelligence evolving towards greater : sophistication power

• Homo Cyber Sapiens ↔ technological extensions of the human brain.

Page 10: Artificial life

10

Homo Cyber Sapiens

• Artificial brain extensions should mimic the operation of human neurophysiology. Neural modeling is implemented in chips

• Artificial brain may be completely different from natural brain. The build of bridges will establish data communication and

processing.

Page 11: Artificial life

11

History

• Brief History of Homo Cyber Sapiens/Post Humans.• Mary Shelley : Frankenstein (1831)• K.Eric Drexler (1980-1990) : Nanotechnology

Page 12: Artificial life

12

Evolution of Super Computer

Fig.1 Projection of supercomputer speed

• Brain versus Super Computers Ian Pearson, Chris Winter & Peter Cochrane (1995)

Page 13: Artificial life

13

Use Case

• Two Examples :

Page 14: Artificial life

Artificial Life

Intelligent Systemsor Robot Homonidus

Intelligens

Page 15: Artificial life

15

Intelligent systems

• Cybernetic and Artificial Intelligence : already 50 years of experiment

• Many advantages for computer science

• A whole range of programs exhibit features of human intelligence

• But …

Page 16: Artificial life

16

Limits of Intelligent systems

• Steels : 3 strong limits of Intelligent systems

a ‘frozen intelligence’ and not an intelligent behavior

intelligence needs to be embodied

consciousness

Page 17: Artificial life

17

First limit : frozen intelligence

• Expensive cost of construction

• Ephemeral validity

• Outdated by changes

• Expensive and unrealistic maintenance

Something more than knowledge needed to be intelligent

Page 18: Artificial life

18

Second limit : lack of embodiment

• Knowledge systems : disembodied intelligence no direct link to the real world

• Intelligent behavior emerges from interactions

• Difficulties : link between the real world and the system symbols adaptation to unforeseen actions

Page 19: Artificial life

19

Third limit : consciousness

• An intelligent system needs a sense of self and a conscience

Possible ? Existence of a true autonomous agent ?

Page 20: Artificial life

20

State of research in 1995

• No technological obstacle

• The real obstacle : the lack of a theory of intelligence

Page 21: Artificial life

21

State of research in 2005 (1/2)

• Knowledge systems : example of ‘frozen intelligence’

• Case Based Reasoning use the last experience

• Multi-agent systems : agents environment interactions

Fig 1. A robot soccer team by Nikos Vlassis (Amsterdam)

Page 22: Artificial life

22

State of research in 2005 (2/2)

• McCarthy (1995-2002) : consciousness does not yet exist in intelligent system

Intelligent systems

emotions

sub consciousness introspection

consciousness

Page 23: Artificial life

Artificial Life

The Artificial life approach :

Theoretical approach

Page 24: Artificial life

24

Historic (1/2)

“ ‘Intelligent machinery’ , It’s the birth of the concept of intelligent machines.”

1940

1948

1970

1980

1987

2005

Connectionism

John Conway

Alan Turing

John Von Neumann

Christopher Langton

cellular automat

first scientific conference devoted to A-life

game of life : simple system → complex self-organized structures

parallel, distributed processing, neural networksAI ↔ cognitive science

Page 25: Artificial life

25

Historic (2/2)

• Game of life : illustration

Fig 1. Random start Fig 2. Stable state

Page 26: Artificial life

26

Definitions of A-life (1/2)

• Langton (1989) : Artificial life (A-life) : study of ‘natural’ life by attempting to

recreate biological phenomena from scratch within computers and other ‘artificial’ media.

• Rennard (2002) : Life : state of what is not inert.

Artificial life : field of research witch intend to specify the preceding definition.

Page 27: Artificial life

27

Definitions of A-life (2/2)

• Doyne Farmer and d'A.Belin (1992) : A-Life as field of alive

An artificial life must : be initiated by man be autonomous be in interaction with its environment induce the emergence of behaviors

Optional : capacity to reproduce capacities of adaptation

Page 28: Artificial life

28

Steels’ vision of A-life

• Dynamic system theory applied to Artificial Intelligence

• A-life → Unified theory of cognition

• Unified theory : explain the details of all mechanisms of all problems within some domain.

unified theory of cognition domain’s ↔ all cognitive behavior of humans.

experimental psychology could support such theories. (Newell 1990)

Page 29: Artificial life

29

Steels’ research path

• Two kinds of behavior expected :

differentiation : individual agent get specific task

recognition : make the difference between the member of the group and those which don’t.recognition → emergence of language.

Page 30: Artificial life

30

Axes of research (1/2)

• Emergence of language (Steels & Kaplan)

Emergence of common sense

Adaptation to other agents

Page 31: Artificial life

31

Axes of research (2/2)

• Autonomous robotic (Floreano)

Genetic algorithms with neural networks

Co-evolution

• Animat Approach (Meyer)

Synthesizing animal intelligence

Situated and incarnate cognition

Page 32: Artificial life

Artificial Life

The Artificial life approach :

Experimental approach

Page 33: Artificial life

33

Steels’ experimentation – 1995 (1/4)

• A complete artificial ecosystem

• An environment with different pressures for the robots

• Robots are required to do some work which is paid in energy

• Cooperation and competition with each other

• Behavior systems

Page 34: Artificial life

34

Steels’ experimentation – 1995 (2/4)

Fig 1. The ecosystem with the charging station, a robot vehicle, and a competitor

Fig 2. A robot vehicle

Page 35: Artificial life

35

Steels’ experimentation – 1995 (3/4)

Environment Perception

- Visual Perception ModulesCharging station, Competitors, Other robots

- SensorsLight, Tactile

Behavior system

- Finding resources- Exploring

- Obstacle avoidance - Align on charging station- Align on competitors

- Turn left/right, Forward, Retract, Stop

- Motors

Page 36: Artificial life

36

Steels’ experimentation – 1995 (4/4)

• Interesting results :

Behavior diversification Hard working gourp Lazy group

Steels : something could emerge from the lazy group

Page 37: Artificial life

37

Steel’s experimentation – 2001 (1/3)

• One speaker (S), one hearer (H)

• H tries to guess what S is talking about

• H guess wrong : correction (feedback)

• No explicit object designation : simple region pointing

Page 38: Artificial life

38

Steel’s experimentation – 2001 (2/3)

Fig 3. The talking heads experiment

Page 39: Artificial life

39

Steel’s experimentation – 2001 (3/3)

• Interesting results :

Emergence of a shared word Winner-take-all Shared word repertoires after experiment

Page 40: Artificial life

40

Other kind of experimentation (1/2)

Floreano & al. (2004)• Evolution of Spiking Neural Networks in robots• Objective : Vision-based navigation and wall avoidance

Fig 4. A Khepera robot in a square arena

Fig 5. A Khepera robot

Page 41: Artificial life

41

Other kind of experimentation (2/2)

• Interesting results :

Avoiding walls following with security distance Biologically plausible connection patterns Forward progression Self adaptable speed : body adaptation

Page 42: Artificial life

Artificial Life

Conclusion

Page 43: Artificial life

43

Conclusion (1/3)

• 3 approaches

Bionic man : ethic problems

Intelligent systems : limits

Artificial life : Tremendous possibilities Involving many fields, biologically-inspired Now a days the biological approach stay in progress.

Page 44: Artificial life

44

Conclusion (2/3)

• Lack of intelligence theory

• Problem of consciousness in robots

• Is language needed for intelligence ?

• Sufficient pressures for a new species ?

• Does performance gain means Intelligence gain ?

Page 45: Artificial life

45

Conclusion (3/3)

“Intelligence is like life or cosmos; its such a deepphenomenon that we will still be trying to

understand itmany centuries from now.”

Luc Steels

Page 46: Artificial life

46

Page 47: Artificial life

47

Homo Cyber Sapiens

• The Anatomical changes are defined by :

New sensory modalities.

• The Extreme ecological pressures are defined by:

Homo erectus

Homo Sapiens “wise man"

Homo erectus

Homo Sapiens “wise man"

Page 48: Artificial life

48

Homo Cyber Sapiens

• The human species is today under just as much stress as it must have been in the past,Still Human Intelligence haven’t evolved !

• How realistic is the development of a Homo Cyber Sapiens ?