Investigating an A-star algorithm-based fitness function for mobile robot evolution

Shanker Prabhu, Peter Kyberd, Jodie Wetherall

Research output: Chapter in Book/Report/Conference proceedingConference contribution

26 Downloads (Pure)

Abstract

One of the factors that affect the success of Evolutionary Robotics (ER) is the way fitness functions are designed to operate. While needs-based custom fitness functions have been developed, most of the time they have been defined in simpler mathematical functions to reduce the computation time. In this paper, we hypothesize that an incremental fitness function based on established techniques in specific task domains in robotics will aid the evolution process. An A-star algorithm-based fitness function for path planning is designed and implemented for evolving the body plans and controllers of robots for navigation and obstacle avoidance tasks. It has been shown that using this concept, fitter robots have evolved in most cases when compared to simple distance-only based fitness functions. However, due to variable performance of the evolver with the A-star fitness function, the results are inconclusive. We also identify problems associated with the fitness function and make recommendations for designing future fitness functions based on observations of the experiments.

Original languageEnglish
Title of host publication2018 22nd International Conference on System Theory, Control and Computing, ICSTCC 2018 - Proceedings
EditorsRazvan Solea, Marian Barbu, Adrian Filipescu
PublisherIEEE
Pages771-776
Number of pages6
ISBN (Electronic)978-1-5386-4444-7
ISBN (Print)978-1-5386-4445-4
DOIs
Publication statusPublished - 22 Nov 2018
Event22nd International Conference on System Theory, Control and Computing - Sinaia, Romania
Duration: 10 Oct 201812 Oct 2018

Publication series

NameIEEE ICSTCC Proceedings Series
PublisherIEEE
ISSN (Print)2372-1618

Conference

Conference22nd International Conference on System Theory, Control and Computing
Abbreviated titleICSTCC 2018
Country/TerritoryRomania
CitySinaia
Period10/10/1812/10/18

Keywords

  • A-star Algorithm
  • Co-evolution
  • Evolutionary Robotics
  • Fitness Function

Fingerprint

Dive into the research topics of 'Investigating an A-star algorithm-based fitness function for mobile robot evolution'. Together they form a unique fingerprint.

Cite this