Terrain prediction for an eight-legged robot

Stephen Urwin-Wright, David Sanders, Sheng Chen

    Research output: Contribution to journalArticlepeer-review


    Most legged robots must negotiate unknown environments with little or no terrain knowledge, as autonomous terrain mapping for robots is limited. A predictive terrain contour mapping strategy is proposed, which employs the use of a feed-forward neural network to predict the contours in environments, based on the positions of the neighboring legs. The predicted performance is better than previous implementations.
    Original languageEnglish
    Pages (from-to)91-98
    JournalJournal of Robotic Systems
    Issue number2
    Early online date16 Jan 2002
    Publication statusPublished - Feb 2002


    • Terrain prediction
    • mobile
    • robot
    • legged,


    Dive into the research topics of 'Terrain prediction for an eight-legged robot'. Together they form a unique fingerprint.

    Cite this