Unsupervised Place Discovery for Visual Place Classification
This addresses a specific challenge in robotic mapping and localization, but it is incremental as it builds on existing DCNN methods for place classification.
The study tackled the chicken-and-egg problem of partitioning a robot's workspace into places for visual place classification using DCNNs, by proposing several unsupervised strategies for place discovery and evaluating them on the NCLT dataset.
In this study, we explore the use of deep convolutional neural networks (DCNNs) in visual place classification for robotic mapping and localization. An open question is how to partition the robot's workspace into places to maximize the performance (e.g., accuracy, precision, recall) of potential DCNN classifiers. This is a chicken and egg problem: If we had a well-trained DCNN classifier, it is rather easy to partition the robot's workspace into places, but the training of a DCNN classifier requires a set of pre-defined place classes. In this study, we address this problem and present several strategies for unsupervised discovery of place classes ("time cue," "location cue," "time-appearance cue," and "location-appearance cue"). We also evaluate the efficacy of the proposed methods using the publicly available University of Michigan North Campus Long-Term (NCLT) Dataset.