Swarm Robotics Lecturer: Roderich Gross Companion slides for the - - PowerPoint PPT Presentation

▶
swarm robotics
SMART_READER_LITE
LIVE PREVIEW

Swarm Robotics Lecturer: Roderich Gross Companion slides for the - - PowerPoint PPT Presentation

Jan 03, 2024 662 likes •1.08k views

Swarm Robotics Lecturer: Roderich Gross Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, 1 Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press Outline Why swarm robotics? Example domains:

slide-1
SLIDE 1

Swarm Robotics

Lecturer: Roderich Gross

1 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-2
SLIDE 2

Outline

Why swarm robotics? Example domains:

  • Coordinated exploration
  • Transportation and clustering
  • Reconfigurable robots

Summary Stigmergy revisited Stigmergy revisited

2 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-3
SLIDE 3

Sources of Inspiration

3 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-4
SLIDE 4

Example

4 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-5
SLIDE 5

Key Properties

  • Composed of many individuals
  • The individuals are

relatively homogeneous.

  • The individuals are relatively incapable.
  • The interactions among the individuals

The interactions among the individuals are based on simple behavioral rules that exploit only local information.

  • The overall behavior results

from a self-organized process.

5 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-6
SLIDE 6

Technological Motivations

  • Robustness
  • Scalability
  • Versatility / flexibility
  • Super linearity
  • Low cost?
  • Low cost?

6 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-7
SLIDE 7

Coordinated Exploration

  • 1. Environmental monitoring

2 Pheromone robotics

  • 2. Pheromone robotics
  • 3. Chaining

7 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-8
SLIDE 8

Example 1: Environmental Monitoring

  • Swarm of mobile robots for localizing an odor source
  • Simple behaviors based on odor and wind detection
  • Communication can help to increase the efficiency.

Hayes et al., 2002

8 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-9
SLIDE 9

Example 2: Pheromone Robotics

  • robot dispersion

robot dispersion

  • gradient (via hop counts)
  • shortest path
  • shortest path
  • pheromone diffussion / evaporation

Payton et al., 2005

9 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-10
SLIDE 10

Example 3: Chaining

  • Limited sensing range

Si li f l (di ti l h i )

  • Signaling of colors (directional chains)

Nouyan et al., 2009

10 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-11
SLIDE 11

Example 3: Chaining (Cont.)

Mondada et al., 2005

Chains in prey retrieval (division of labor)

Nouyan et al., 2009

11 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-12
SLIDE 12

Transportation and Clustering

  • 1. Coordinated box pushing

2 Blind bulldozing

  • 2. Blind bulldozing
  • 3. Clustering

C

  • 4. Cooperative Manipulation

12 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-13
SLIDE 13

Example 1: Coordinated Box Pushing

Kube and Zhang, 1993; Kube and Bonabeau, 2000

  • Task requires cooperation
  • No explicit communication

No explicit communication

  • Behavior-based approach
  • Ant-inspired stagnation recovery mechanism
  • Ant-inspired stagnation recovery mechanism

al., 1978 dobler et a Hoelld

13 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-14
SLIDE 14

Example 2: Blind Bulldozing

Force iti sensitive plow Nest construction by ants

Franks et al., 1992

Nest construction by robots

Parker et al., 2003

14

, ,

Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-15
SLIDE 15

Example 3: Clustering

Clustering and sorting behavior can be observed in several ant species. Important mechanisms:

  • stigmergic communication
  • stigmergic communication
  • positive & negative feedback

Example rule (N = #objects experienced in a short time window):

  • 1. Probability to pick up an object: inversely proportional to N
  • 2. Probability to deposit an object: directly proportional to N

y p j y p p Cemetery clusters in Messor sancta, in Messor sancta, 26 hours in total, 1500 corpses

15 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-16
SLIDE 16

Example 4: Cooperative Manipulation

Desert ants cooperate to pull out of the ground long sticks (too long for a single ant). This behavior can be reproduced with a group of robots with a group of robots. How long to wait for a teammate? Super-linear performance: # sticks retrieved per robot is optimal for ca 6 robot groups is optimal for ca. 6-robot groups.

Ijspeert et al., 2001

16 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-17
SLIDE 17

Reconfigurable Robots

A modular robot, usually composed of several identical components, which can be re-organized to create p , g morphologies suitable for different tasks. Inspiration: Inspiration:

  • cells (cellular automata)
  • individuals (swarm intelligence)
  • Chain-type reconfigurable robots
  • Lattice-type reconfigurable robots
  • Mobile reconfigurable robots
  • Further types of reconfigurable robots

17 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-18
SLIDE 18

Reconfigurable Robots

18 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-19
SLIDE 19

Chain Type Example: CONRO

  • Fully self-contained

Pin hole connector (+latch)

  • Pin-hole connector (+latch)
  • Infrared-based guidance
  • Docking relatively complex

Docking relatively complex

  • Good mobility

ISI, USC; Castano et al., 2000

19 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-20
SLIDE 20

Chain Type Example: CONRO

Control can cope with s dden changes in the sudden changes in the robot’s morphology.

AdapTronics Group & ISI, USC

20 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-21
SLIDE 21

Chain Type Example: PolyBot

PARC, 2000; Yim et al., 2002

Self-reconfiguration of PolyBot

  • 1 DOF module
  • Power PC 555

E t ll d

  • Externally powered

21 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-22
SLIDE 22

Lattice Type Example: A-TRON

  • Two half-spheres
  • 4 male and 4 female connectors
  • Self-docking is relatively simple.

Self reconfiguration can require

  • Self-reconfiguration can require

many steps.

The Maersk McKinney Moller Inst., Univ. of Southern Denmark

22 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-23
SLIDE 23

Lattice Type Example: A-TRON

The Maersk McKinney Moller Inst., Univ. of Southern Denmark

23 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-24
SLIDE 24

Hybrid Example: M-TRAN

M-TRAN III (2005 -)

  • Hybrid: lattice type & chain type
  • Magnets or actuated mechanical hooks
  • Magnets or actuated mechanical hooks
  • Cellular Automata rules

AIST; Murata et al., 2002

24 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-25
SLIDE 25

Physical Cooperation of Mobile Individuals

Passing a gap Nest building Gro ped Fall Grouped Fall Plugging potholes in the trail

25 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-26
SLIDE 26

From Swarming Ants to Swarm-bots

26 Laboratory of Intelligent Systems http://lis.epfl.ch 26

Autonom ous System s Lab http:/ / asl.epfl.ch

slide-27
SLIDE 27

Mobile Reconfigurable Robots

Mobile units assemble into connected entities that are larger and stronger than any individual unit. g g y

Mondada et al., 2005; Gross et al., 2006

27 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-28
SLIDE 28

Example: Search & Rescue

28 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-29
SLIDE 29

Example: Search & Rescue (Cont.)

29 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-30
SLIDE 30

Other Types of Reconfigurable Robots yp g

  • Relative displacement without moving parts
  • Electro-magnet rings
  • Electro-magnet rings
  • Conversion of electrical to kinetic energy

Claytronics

Goldstein et al., 2005

30 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-31
SLIDE 31

Other Types of Reconfigurable Robots yp g

Stochastic reconfiguration of passively moving parts PPT

  • Univ. of Washington; Klavins et al., 2005

31 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-32
SLIDE 32

“Hierarchical” Organization

Meta-modules 1 Anatomy-based 2 Meta modules Anatomy based

1,2 The Maersk McKinney Moller Inst., Univ. of Southern Denmark 2 Intel Research Pittsburgh

32 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-33
SLIDE 33

Summary

Swarm Intelligence: Key properties and technological motivations Key properties and technological motivations Coordinated Exploration Physical cooperation in ants and robots Reconfigurable robots

33 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-34
SLIDE 34

Stigmergy Revisited

Communication through modification of the environment. The result of work by an individual leaves a persistent sign The result of work by an individual leaves a persistent sign that affects the actions of (possibly other) individuals. Stimuli-response loop Stimuli-response loop

From Camazine et al., 2001 (Smith, 1978)

34 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-35
SLIDE 35

Stigmergy Revisited

Testing how building activities are coordinated. Redundant structures

Hole incorporated Hole incorporated by human

From Camazine et al., 2001 (Smith, 1978)

35 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-36
SLIDE 36

Stigmergy Revisited

Nest construction rules (wasp combs)

Camazine et al., 2001

36 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-37
SLIDE 37

Stigmergy Revisited

Deterministic rule:

Add cell to corner area if 2 or 3 adjacent walls are present.

Probabilistic rule:

Camazine et al., 2001

37 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-38
SLIDE 38

Stigmergy – Distributed Construction

Grushin and Reggia, 2006

38 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press

slide-39
SLIDE 39

Termites Video

h // b / h? 7 dG f QU Attenborough (BBC) http://www.youtube.com/watch?v=0m7odGafpQU

39 Companion slides for the book Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies by Dario Floreano and Claudio Mattiussi, MIT Press