Automated synthesis of control algorithms from first principles

Authors:
Henrik Berg;Roland Olsson;Per-Olav Rusås;Morgan Jakobsen
Affiliations:
Norwegian Defence Research Establishment, Horten, Norway;Faculty of Computer Science, Østfold University College, Halden, Norway;Prediktor AS, Fredrikstad, Norway;Kongsberg Norcontrol IT, Horten, Norway
Venue:
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Year:
2009

Citing 9
Cited 1

Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Inductive functional programming using incremental program transformation

Artificial Intelligence
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Evolution and Optimum Seeking: The Sixth Generation

Evolution and Optimum Seeking: The Sixth Generation
Machine Learning

Machine Learning
Learning to Race: Experiments with a Simulated Race Car

Proceedings of the Eleventh International Florida Artificial Intelligence Research Society Conference
Stanley: The robot that won the DARPA Grand Challenge: Research Articles

Journal of Robotic Systems - Special Issue on the DARPA Grand Challenge, Part 2
Automatic design of pulse coupled neurons for image segmentation

Neurocomputing
Online speed adaptation using supervised learning for high-speed, off-road autonomous driving

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence

Using automatic programming to generate state-of-the-art algorithms for random 3-SAT

Journal of Heuristics

Quantified Score

Hi-index	0.00

Visualization

Abstract

A variety of machine learning techniques have been employed to automatically create control algorithms for autonomous vehicles. Much research has focused on various "black box" approaches, in which the synthesized or learned control algorithms perform well when tested, but are difficult or impossible to analyze and understand. This paper presents the use of the ADATE system to evolve a control algorithm based on a racing car simulator. The system evolved compact and analyzable yet sophisticated control algorithms capable of driving millions of randomly generated tracks at high speeds without ever driving off the road. The approach presented is likely to be applicable to most automatic control problems, given a set of training examples and a suitable software simulator.