Flocking with GA/PSO SI Course Project Yvan Bidiville & Thomas - - PowerPoint PPT Presentation

▶
flocking with ga pso
SMART_READER_LITE
LIVE PREVIEW

Flocking with GA/PSO SI Course Project Yvan Bidiville & Thomas - - PowerPoint PPT Presentation

Feb 27, 2024 148 likes •246 views

Flocking with GA/PSO SI Course Project Yvan Bidiville & Thomas Thurnherr The Goal Evolve a controller for robots to move as flock. Explore the effectiveness of GA and PSO, with both homogeneous and heterogeneous learning. The

slide-1
SLIDE 1

Flocking with GA/PSO

SI Course Project Yvan Bidiville & Thomas Thurnherr

slide-2
SLIDE 2

The Goal

  • Evolve a controller for robots to move

as flock.

  • Explore the effectiveness of GA and

PSO, with both homogeneous and heterogeneous learning.

slide-3
SLIDE 3

The Idea Behind the Given Code

Neural Network

slide-4
SLIDE 4

The First Try

Neural Network

Average Direction

slide-5
SLIDE 5

Problems

  • Assuming too much information on the

robots side: They cannot figure out the direction of their neighbours.

  • Bad approach, which does not really

make use of the neural network.

slide-6
SLIDE 6

The Second Try

Neural Network

slide-7
SLIDE 7

The Fitness Function

  • Former fitness function:

fit[i] = 1.0 - #neighbours/#robots

  • New fitness function

fit[i] = 1.0 - (#neighbours/#robots) · min(1.0, d[i]), where d[i] = (xlast[i] - xfirst[i])2 + (ylast[i] - yfirst[i])2, with x and y coordinates of the centre of mass.

  • Fitness value within the interval [0, 1]
slide-8
SLIDE 8

Webots-Movie of a Simulation

QuickTime™ and a decompressor are needed to see this picture.

slide-9
SLIDE 9

Any Questions?