In this paper we are interested in autonomous vehicles that can automatically develop terrain classifiers without human interaction or feedback. A key issue is the clustering of time-series data collected by the sensors of a ground-based vehicle moving over several terrain surfaces (e.g. concrete or soil). In this context, we present a novel off-line windowless clustering algorithm that exploits time-dependency between samples. In terrain coverage, sets of sensory measurements are returned that are spatially, and hence temporally, correlated. Our 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 the change in classifier probability estimates over time. The main advantage over other existing methods is its 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 time interval that the system stays in a single state. The algorithm was evaluated using three different classifiers (linear separator, mixture of Gaussians and k-Nearest Neighbor), over both synthetic data sets and two different mobile robotic platforms, with success. Comparisons are provided against a window-based algorithm and against a hidden Markov model trained with Expectation- Maximization, with positive results.
Clustering sensor data for autonomous terrain identification using time-dependency
Autonomous Robots ; 26 , 2-3 ; 171-186
2009
16 Seiten, 19 Quellen
Aufsatz (Zeitschrift)
Englisch
Klassiermaschine , Kosten-Nutzen-Analyse , Kostenfunktion , Ausbildung (Bildungswesen) , Bildsegmentierung , mobiler Roboter , Navigation , Objekterkennung , Roboter , Sensor , Unterricht , Cluster-Bildung , maschinelles Lernen , Zeitintervall , Optimierungsalgorithmus , statistisches Verfahren , autonomes Fahrzeug
Clustering sensor data for autonomous terrain identification using time-dependency
British Library Online Contents | 2009
|