Long-Term Ensemble Learning of Visual Place Classifiers

This paper addresses the problem of cross-season visual place classification (VPC) from a novel perspective of long-term map learning. Our goal is to enable transfer learning efficiently from one season to the next, at a small constant cost, and without wasting the robot's available long-term-m...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-09
Main Authors: Fei, Xiaoxiao, Tanaka, Kanji, Fang, Yichu, Takayama, Akitaka
Format: Article
Language:English
Subjects:
Artificial neural networks
Classifiers
Ensemble learning
Neural networks
Partitioning
Retraining
Robots
Scheduling
Task scheduling
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper addresses the problem of cross-season visual place classification (VPC) from a novel perspective of long-term map learning. Our goal is to enable transfer learning efficiently from one season to the next, at a small constant cost, and without wasting the robot's available long-term-memory by memorizing very large amounts of training data. To realize a good tradeoff between generalization and specialization abilities, we employ an ensemble of convolutional neural network (DCN) classifiers and consider the task of scheduling (when and which classifiers to retrain), given a previous season's DCN classifiers as the sole prior knowledge. We present a unified framework for retraining scheduling and discuss practical implementation strategies. Furthermore, we address the task of partitioning a robot's workspace into places to define place classes in an unsupervised manner, rather than using uniform partitioning, so as to maximize VPC performance. Experiments using the publicly available NCLT dataset revealed that retraining scheduling of a DCN classifier ensemble is crucial and performance is significantly increased by using planned scheduling.
ISSN:2331-8422