How Useful is Lifelong Evolution for Robotics

Joanne Heather Walker, Myra Scott Wilson

Research output: Chapter in Book/Report/Conference proceedingConference Proceeding (Non-Journal item)


This paper investigates a system that uses a genetic algorithm to train a robot for a generalised test environment, then an evolutionary strategy to investigate the effect of continuing the evolution as the robot progresses with its task. The paper concludes that continuing evolution after a training phase has an important role to play in producing truly adaptive robots.
Original languageEnglish
Title of host publicationFrom animals to animats 7
Subtitle of host publicationProceedings of the Seventh International Conference on Simulation of Adaptive Behavior
EditorsB. Hallam, D. Floreano, J. Meyer, G. Hayes
PublisherMIT Press
Number of pages2
ISBN (Print)9780262291170
Publication statusPublished - 2002


Dive into the research topics of 'How Useful is Lifelong Evolution for Robotics'. Together they form a unique fingerprint.

Cite this