Abstract
This paper presents a new integration model for on-line topological map building with environment slow features detection. The proposed model is formed by the integration of Bayesian Adaptive Resonance Associative Memory (BARAM) and Incremental Slow Feature Analysis (IncSFA). IncSFA incrementally extracts slowly varying features from a rapidly changing input signal. These slow features will be fed to BARAM for environment learning to build a topological map. The explored environment is represented as a set of neurons (nodes) and edges that connecting all nodes. Each neuron represents a distinct place and edges store robot traverse information that leads the robot to travel from one node to another. The proposed model is an unsupervised learning technique that does not require any prior knowledge of what an environment is supposed to be for ease of implementation. The effectiveness of our proposed method is validated by several standardized benchmark datasets.
| Original language | English |
|---|---|
| Title of host publication | MHS 2018 - 2018 29th International Symposium on Micro-NanoMechatronics and Human Science |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9781538667927 |
| DOIs | |
| Publication status | Published - Dec 2018 |
| Event | 29th International Symposium on Micro-NanoMechatronics and Human Science, MHS 2018 - Nagoya, Japan Duration: Dec 10 2018 → Dec 12 2018 |
Publication series
| Name | MHS 2018 - 2018 29th International Symposium on Micro-NanoMechatronics and Human Science |
|---|
Conference
| Conference | 29th International Symposium on Micro-NanoMechatronics and Human Science, MHS 2018 |
|---|---|
| Country | Japan |
| City | Nagoya |
| Period | 12/10/18 → 12/12/18 |
Fingerprint
ASJC Scopus subject areas
- Artificial Intelligence
- Electrical and Electronic Engineering
- Mechanical Engineering
- Control and Optimization
- Instrumentation
- Human-Computer Interaction
Cite this
An Episodic Memory Model with Slow Features Extraction for Topological Map Building. / Chin, Wei Hong; Toda, Yuichiro; Kubota, Naoyuki; Woo, Jinseok; Loo, Chu Kiong.
MHS 2018 - 2018 29th International Symposium on Micro-NanoMechatronics and Human Science. Institute of Electrical and Electronics Engineers Inc., 2018. 8887062 (MHS 2018 - 2018 29th International Symposium on Micro-NanoMechatronics and Human Science).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - An Episodic Memory Model with Slow Features Extraction for Topological Map Building
AU - Chin, Wei Hong
AU - Toda, Yuichiro
AU - Kubota, Naoyuki
AU - Woo, Jinseok
AU - Loo, Chu Kiong
PY - 2018/12
Y1 - 2018/12
N2 - This paper presents a new integration model for on-line topological map building with environment slow features detection. The proposed model is formed by the integration of Bayesian Adaptive Resonance Associative Memory (BARAM) and Incremental Slow Feature Analysis (IncSFA). IncSFA incrementally extracts slowly varying features from a rapidly changing input signal. These slow features will be fed to BARAM for environment learning to build a topological map. The explored environment is represented as a set of neurons (nodes) and edges that connecting all nodes. Each neuron represents a distinct place and edges store robot traverse information that leads the robot to travel from one node to another. The proposed model is an unsupervised learning technique that does not require any prior knowledge of what an environment is supposed to be for ease of implementation. The effectiveness of our proposed method is validated by several standardized benchmark datasets.
AB - This paper presents a new integration model for on-line topological map building with environment slow features detection. The proposed model is formed by the integration of Bayesian Adaptive Resonance Associative Memory (BARAM) and Incremental Slow Feature Analysis (IncSFA). IncSFA incrementally extracts slowly varying features from a rapidly changing input signal. These slow features will be fed to BARAM for environment learning to build a topological map. The explored environment is represented as a set of neurons (nodes) and edges that connecting all nodes. Each neuron represents a distinct place and edges store robot traverse information that leads the robot to travel from one node to another. The proposed model is an unsupervised learning technique that does not require any prior knowledge of what an environment is supposed to be for ease of implementation. The effectiveness of our proposed method is validated by several standardized benchmark datasets.
UR - http://www.scopus.com/inward/record.url?scp=85075023416&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075023416&partnerID=8YFLogxK
U2 - 10.1109/MHS.2018.8887062
DO - 10.1109/MHS.2018.8887062
M3 - Conference contribution
AN - SCOPUS:85075023416
T3 - MHS 2018 - 2018 29th International Symposium on Micro-NanoMechatronics and Human Science
BT - MHS 2018 - 2018 29th International Symposium on Micro-NanoMechatronics and Human Science
PB - Institute of Electrical and Electronics Engineers Inc.
ER -