Robotics: Science and Systems IV

Clustering Sensor Data for Terrain Identification using a Windowless Algorithm

Philippe Giguere, Gregory Dudek

Abstract: In this paper we consider autonomous terrain classification using contact feedback. We are interested in autonomous systems that can automatically develop terrain classifiers without human interaction of feedback. In this context, we present a novel off-line windowless clustering algorithm exploiting time-dependency between samples. In terrain coverage, sets of sensory measurements are returned that are spatially, and hence temporally correlated. This algorithm works by finding a set of parameter values for a user-specified classifier that minimize a cost function. This cost function is related to change in classifier probability outputs over time. The main advantage over other existing methods is the ability to cluster data for fast-switching systems that either have high process or observation noise, or complex distributions that cannot be properly characterized within the average duration of a state. The algorithm was tested with three different classifiers (linear separator, mixture of Gaussians and k-Nearest Neighbor), over synthetic and actual robot sensor data sets, all with success.



    AUTHOR    = {Philippe Giguere, Gregory Dudek},
    TITLE     = {Clustering Sensor Data for Terrain Identification using a Windowless Algorithm},
    BOOKTITLE = {Proceedings of Robotics: Science and Systems IV},
    YEAR      = {2008},
    ADDRESS   = {Zurich, Switzerland},
    MONTH     = {June},
    DOI       = {10.15607/RSS.2008.IV.004}