Driving Cars by Means of Genetic Algorithms

Authors:
Yago Saez;Diego Perez;Oscar Sanjuan;Pedro Isasi
Affiliations:
Carlos III University, Madrid, Spain 28911;Carlos III University, Madrid, Spain 28911;Oviedo University, Oviedo, Spain 33002;Carlos III University, Madrid, Spain 28911
Venue:
Proceedings of the 10th international conference on Parallel Problem Solving from Nature: PPSN X
Year:
2008

Citing 6
Cited 1

Rapidly Adapting Machine Vision for Automated Vehicle Steering

IEEE Expert: Intelligent Systems and Their Applications
Coevolution of active vision and feature selection

Biological Cybernetics
Ohio State University at the 2004 DARPA Grand Challenge: Developing a Completely Autonomous Vehicle

IEEE Intelligent Systems
Evolution of driving agent, remotely operating a scale model of a car with obstacle avoidance capabilities

Proceedings of the 8th annual conference on Genetic and evolutionary computation
Evolving controllers for simulated car racing using object oriented genetic programming

Proceedings of the 9th annual conference on Genetic and evolutionary computation
Arms races and car races

PPSN'06 Proceedings of the 9th international conference on Parallel Problem Solving from Nature

Generalization of TORCS car racing controllers with artificial neural networks and linear regression analysis

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The techniques and the technologies supporting Automatic Vehicle Guidance are an important issue. Automobile manufacturers view automatic driving as a very interesting product with motivating key features which allow improvement of the safety of the car, reducing emission or fuel consumption or optimizing driver comfort during long journeys. Car racing is an active research field where new advances in aerodynamics, consumption and engine power are critical each season. Our proposal is to research how evolutionary computation techniques can help in this field. As a first goal we want to automatically learn to drive, by means of genetic algorithms, optimizing lap times while driving through three different circuits.