Artificial Life and Robotics

, Volume 1, Issue 1, pp 35–38 | Cite as

Artificial evolution and real robots

  • Inman Harvey
Original Paper

Abstract

Artificial evolution as a design methodology allows the relaxation of many of the constraints that have held back conventional methods. It does not require a complete prior analysis and decomposition of the task to be tackled, as human designers require. However, this freedom comes at some cost; there are a whole new set of issues relating to evolution that must be considered. Standard genetic algorithms may not be appropriate for incremental evolution of robot controllers. Species adaptation genetic algorithms, (SAGA) have been developed to meet these special needs. The main cost of an evolutionary approach is the large number of trials that are required. Simulations-especially those involving vision in complex environments, or modeling detailed semiconductor physics—may not be adequate or practical. Examples of evolved robots will be discussed, including a specialized piece of equipment which allows a robot to be tested using simple vision in real time, and what is believed to be the first successful example of an evolved hardware controller for a robot.

Key words

artificial evolution genetic algorithms evolutionary robotics 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Brooks RA (1986) A robust layered control system for a mobile robot. IEEE J Robot Autom 2: 14–23MathSciNetGoogle Scholar
  2. 2.
    Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Addison-Wesley, Reading, MAMATHGoogle Scholar
  3. 3.
    Holland J (1975) Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor, MAGoogle Scholar
  4. 4.
    Harvey I (1992) Species adaptation genetic algorithms: The basis for a continuing SAGA. In: Varela F, Bourgine P (eds) Toward a practice of autonomous systems, MIT Press/Bradford Books, Cambridge, MA, pp 346–354Google Scholar
  5. 5.
    Kauffman S (1989) Adaptation on rugged fitness landscapes. In: Stein DL (ed) Lectures in the sciences of complexity. Addison Wesley, Reading, MA, pp 527–618Google Scholar
  6. 6.
    Eigen M, McCaskill J, Schuster P (1988) Molecular quasi-species. J Phys Chem 92:6881–6891CrossRefGoogle Scholar
  7. 7.
    Harvey I (1993) Evolutionary robotics and SAGA: The case for hill crawling and tournament selection. In: Langton C (ed) Artificial life III. Addison Wesley, Reading, MA, pp 299–326Google Scholar
  8. 8.
    Koza JR (1990) Genetic programming. Technical report STAN-CS-90-1314, Department of Computer Science, Stanford UniversityGoogle Scholar
  9. 9.
    Beer RD, Gallagher JC (1992) Evolving dynamic neural networks for adaptive behavior. Adapt Behav 1(1):91–122Google Scholar
  10. 10.
    Harvey I, Husbands P, Cliff D (1994) Seeing the light: Artificial evolution, real vision. In: Cliff D, Husbands P, Meyer J-A, Wilson S (eds) From animals to animats vol 3. MIT Press/Bradford Books, Cambridge, MA, pp 392–401Google Scholar
  11. 11.
    Thompson A, Harvey I, Husbands P (1996) Unconstrained evolution and hard consequences. In: Sanchez E, Tomassini M (eds) Towards evolvable hardware. SpringerGoogle Scholar

Copyright information

© ISAROB 1997

Authors and Affiliations

  • Inman Harvey
    • 1
  1. 1.School of Cognitive and Computing SciencesUniversity of SussexBrightonUK

Personalised recommendations