Incrementally Learning Objects by Touch: Online Discriminative and Generative Models for Tactile-Based Recognition

Human beings not only possess the remarkable ability to distinguish objects through tactile feedback but are further able to improve upon recognition competence through experience. In this work, we explore tactile-based object recognition with learners capable of incremental learning. Using the spar...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on haptics Ročník 7; číslo 4; s. 512 - 525
Hlavní autori: Soh, Harold, Demiris, Yiannis
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.10.2014
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Adult
Algorithms
Artificial Intelligence
Classifications
Classifiers
Cluster Analysis
Discriminant Analysis
Female
Grasping
Hand Strength
Humans
Learning
Learning systems
Male
Models, Theoretical
Object recognition
Online
Online Systems
Palpation
Pattern Recognition, Automated - methods
Robotics - methods
Support vector machines
Tactile
Tactile sensors
Teachers
Touch
Training
Unsupervised learning
Young Adult
supervised classification
incremental learning
Tactile object recognition
unsupervised learning
ISSN:1939-1412, 2329-4051, 2329-4051
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Human beings not only possess the remarkable ability to distinguish objects through tactile feedback but are further able to improve upon recognition competence through experience. In this work, we explore tactile-based object recognition with learners capable of incremental learning. Using the sparse online infinite Echo-State Gaussian process (OIESGP), we propose and compare two novel discriminative and generative tactile learners that produce probability distributions over objects during object grasping/ palpation. To enable iterative improvement, our online methods incorporate training samples as they become available. We also describe incremental unsupervised learning mechanisms, based on novelty scores and extreme value theory, when teacher labels are not available. We present experimental results for both supervised and unsupervised learning tasks using the iCub humanoid, with tactile sensors on its five-fingered anthropomorphic hand, and 10 different object classes. Our classifiers perform comparably to state-of-the-art methods (C4.5 and SVM classifiers) and findings indicate that tactile signals are highly relevant for making accurate object classifications. We also show that accurate "early" classifications are possible using only 20-30 percent of the grasp sequence. For unsupervised learning, our methods generate high quality clusterings relative to the widely-used sequential k-means and self-organising map (SOM), and we present analyses into the differences between the approaches.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1939-1412
2329-4051
2329-4051
DOI:10.1109/TOH.2014.2326159