Krzysztof Krawiec


Home

Research:

edit SideBar

In this paper, we use genetic programming (GP) to evolve a vision-driven robot controller capable of navigating in a real-world environment. To this aim, we extract visual primitives from the video stream provided by a camera mounted on the robot and let them to be interpreted by a GP individual. The response of GP expressions is then used to control robot's servos. Thanks to the primitive-based approach, evolutionary process is less constrained in the process of synthesizing image features. Experiments concerning navigation in indoor environment indicate that the evolved controller performs quite well despite very limited human intervention in the design phase.

@INPROCEEDINGS { krawiec08robot,
    AUTHOR = { PaweĊ‚ Gajda and Krzysztof Krawiec },
    TITLE = { Evolving a Vision-Driven Robot Controller for Real-World Indoor Navigation },
    BOOKTITLE = { Applications of Evolutionary Computing },
    YEAR = { 2008 },
    EDITOR = { Mario Giacobini and Anthony Brabazon and Stefano Cagnoni and Gianni A. Di Caro and Rolf Drechsler and Anik\'{o} Ek\'{a}rt and Anna Isabel Esparcia-Alc\'{a}zar and Muddassar Farooq and Andreas Fink and Jon McCormack and Michael O'Neill and Juan Romero and Franz Rothlauf and Giovanni Squillero and A. \c{S}ima Uyar and Shengxiang Yang },
    VOLUME = { 4974 },
    SERIES = { LNCS },
    PAGES = { 184--193 },
    PUBLISHER = { Springer },
    NOTE = { LNCS49740184 },
    ABSTRACT = { In this paper, we use genetic programming (GP) to evolve a vision-driven robot controller capable of navigating in a real-world environment. To this aim, we extract visual primitives from the video stream provided by a camera mounted on the robot and let them to be interpreted by a GP individual. The response of GP expressions is then used to control robot's servos. Thanks to the primitive-based approach, evolutionary process is less constrained in the process of synthesizing image features. Experiments concerning navigation in indoor environment indicate that the evolved controller performs quite well despite very limited human intervention in the design phase. },
    COMMENT = { ProjectELP },
    ISBN = { 978-3-540-78760-0 },
    LOCATION = { Heidelberg },
}


Powered by PmWiki