Title :
Anytime online novelty detection for vehicle safeguarding
Author :
Sofman, Boris ; Bagnell, J. Andrew ; Stentz, Anthony
Author_Institution :
Robot. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
Novelty detection is often treated as a one-class classification problem: how to segment a data set of examples from everything else that would be considered novel or abnormal. Almost all existing novelty detection techniques, however, suffer from diminished performance when the number of less relevant, redundant or noisy features increases, as often the case with high-dimensional feature spaces. Many of these algorithms are also not suited for online use, a trait that is highly desirable for many robotic applications. We present a novelty detection algorithm that is able to address this sensitivity to high feature dimensionality by utilizing prior class information within the training set. Additionally, our anytime algorithm is well suited for online use when a constantly adjusting environmental model is beneficial. We apply this algorithm to online detection of novel perception system input on an outdoor mobile robot and argue such abilities could be key in increasing the real-world applications and impact of mobile robotics.
Keywords :
image classification; image segmentation; mobile robots; object detection; remotely operated vehicles; robot vision; anytime online novelty detection; autonomous unmanned ground vehicles; environmental model; one-class classification problem; outdoor mobile robot; perception system; vehicle safeguarding; Detection algorithms; Fault detection; Humans; Mobile robots; Orbital robotics; Principal component analysis; Robotics and automation; Vegetation mapping; Vehicle detection; Vehicle safety;
Conference_Titel :
Robotics and Automation (ICRA), 2010 IEEE International Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
978-1-4244-5038-1
Electronic_ISBN :
1050-4729
DOI :
10.1109/ROBOT.2010.5509357