Terrain Classification with Crawling Robot Using Long Short-Term Memory Network

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00328018" target="_blank" >RIV/68407700:21230/18:00328018 - isvavai.cz</a>

Result on the web

<a href="https://link.springer.com/chapter/10.1007/978-3-030-01424-7_75" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-01424-7_75</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-01424-7_75" target="_blank" >10.1007/978-3-030-01424-7_75</a>

Result language

angličtina

Original language name

Terrain Classification with Crawling Robot Using Long Short-Term Memory Network

Original language description

Terrain classification is a crucial feature for mobile robots operating across multiple terrains. One way to learn a terrain classifier is to use a stream of labeled proprioceptive data recorded during a terrain traversal. In this paper, we propose a new terrain classifier that combines a feature extraction from a data stream with the long short-term memory (LSTM) network. Features are extracted from the information-sparse data stream by applying a sliding window computing three central moments. The feature sequence is continuously classified by the LSTM network into multiple terrain classes. Furthermore, a modified bagging method is used to deal with a limited and unbalanced training set. In comparison to the previous work on terrain classifiers for a hexapod crawling robot using only servo-drive feedback, the proposed classifier provides continuous classification with the F1 score up to 0.88, and thus provide better results than SVM classifier learned on the same input data.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GA18-18858S" target="_blank" >GA18-18858S: Robotic Lifelong Learning of Multi-legged Robot Locomotion Control in Autonomous Data Collection Missions</a><br>

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2018

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Artificial Neural Networks and Machine Learning – ICANN 2018

ISBN

978-3-030-01423-0

ISSN

0302-9743

e-ISSN

—

Number of pages

10

Pages from-to

771-780

Publisher name

Springer

Place of publication

Basel

Event location

Rhodes

Event date

Oct 4, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000463340000075