Anna Pawlicka

Programmer. Hiker. Cook. Always looking for interesting problems to solve.


About | Archive | Talks

Line following behaviour

15 Apr 2013 | e-puck, genetic algorithm, line following, neural network

I’ve been trying to perfect e-puck’s line following ability and I think I’ve succeeded:

Behaviour was evolved using feedforward neural network and genetic algorithm.

Summary of parameters:
Inputs: 3 (Floor colour sensors)
Outputs: 2 (motor actions)
Number of hidden layers: 1
Number of neurones in a hidden layer: 12
Population size: 30
Selection: Roulette wheel.
Crossover probability: 50%.
Mutation probability: 10%.

Quite good behaviour was evolved after just 10 generations. I’m pretty amazed with how well NN can be trained!


Older · View Archive (25)

Facebook Hackathon

A week ago I attended Women in Computing Hackathon. Theme was “Health & Fitness”. Our team, “Cheetahs”, was working on an app called “Fittah Cheetah”.

Newer

Final year project completed

It’s been a long road, but the project is finally completed: I submitted report and survived my viva :-)