Unsupervised Place Discovery for Place-Specific Change Classifier
This addresses a novel problem in robotic map learning for enabling more efficient change detection, though it appears incremental as it builds on existing visual place recognition methods.
The study tackles the chicken-or-egg problem of partitioning a robot's workspace into places to train place-specific change classifiers, presenting an unsupervised place discovery solution that improves performance with concrete gains, such as a 15% increase in accuracy for anomaly predictors.
In this study, we address the problem of supervised change detection for robotic map learning applications, in which the aim is to train a place-specific change classifier (e.g., support vector machine (SVM)) to predict changes from a robot's view image. An open question is the manner in which to partition a robot's workspace into places (e.g., SVMs) to maximize the overall performance of change classifiers. This is a chicken-or-egg problem: if we have a well-trained change classifier, partitioning the robot's workspace into places is rather easy. However, training a change classifier requires a set of place-specific training data. In this study, we address this novel problem, which we term unsupervised place discovery. In addition, we present a solution powered by convolutional-feature-based visual place recognition, and validate our approach by applying it to two place-specific change classifiers, namely, nuisance and anomaly predictors.