TY - JOUR
T1 - Multi-channel Bayesian Adaptive Resonance Associate Memory for on-line topological map building
AU - Chin, Wei Hong
AU - Seera, Manjeevan
AU - Loo, Chu Kiong
AU - Kubota, Naoyuki
AU - Toda, Yuichiro
N1 - Funding Information:
This research is supported by University of Malaya Grant UM.C/625/1/HIR/MOHE/FCSIT/10 .
Funding Information:
The benchmark datasets were downloaded from the Rawseeds Project, which aims to produce benchmarking tools for robotic systems. The project was funded by the European Commission under the Sixth Framework Programme and it has successfully created and published a high-quality benchmarking toolkit [32,33] . These datasets were used as training samples to validate our proposed method, supplemented by odometry and laser scanner datasets. Fig. 3 a and b illustrates the locations available to the robot during Rawseeds data gathering. Several indoor and outdoor scenarios have been defined by Rawseeds that each generate a dataset.
Publisher Copyright:
© 2015 Elsevier B.V. All rights reserved.
Copyright:
Copyright 2015 Elsevier B.V., All rights reserved.
PY - 2016/1
Y1 - 2016/1
N2 - In this paper, a new network is proposed for automated recognition and classification of the environment information into regions, or nodes. Information is utilized in learning the topological map of an environment. The architecture is based upon a multi-channel Adaptive Resonance Associative Memory (ARAM) that comprises of two layers, input and memory. The input layer is formed using the Multiple Bayesian Adaptive Resonance Theory, which collects sensory data and incrementally clusters the obtained information into a set of nodes. In the memory layer, the clustered information is used as a topological map, where nodes are connected with edges. Nodes in the topological map represent regions of the environment and stores the robot location, while edges connect nodes and stores the robot orientation or direction. The proposed method, a Multi-channel Bayesian Adaptive Resonance Associative Memory (MBARAM) is validated using a number of benchmark datasets. Experimental results indicate that MBARAM is capable of generating topological map online and the map can be used for localization.
AB - In this paper, a new network is proposed for automated recognition and classification of the environment information into regions, or nodes. Information is utilized in learning the topological map of an environment. The architecture is based upon a multi-channel Adaptive Resonance Associative Memory (ARAM) that comprises of two layers, input and memory. The input layer is formed using the Multiple Bayesian Adaptive Resonance Theory, which collects sensory data and incrementally clusters the obtained information into a set of nodes. In the memory layer, the clustered information is used as a topological map, where nodes are connected with edges. Nodes in the topological map represent regions of the environment and stores the robot location, while edges connect nodes and stores the robot orientation or direction. The proposed method, a Multi-channel Bayesian Adaptive Resonance Associative Memory (MBARAM) is validated using a number of benchmark datasets. Experimental results indicate that MBARAM is capable of generating topological map online and the map can be used for localization.
KW - Adaptive resonance theory
KW - Bayesian
KW - Robot navigation
KW - Simultaneous localization and mapping
KW - Topological map
UR - http://www.scopus.com/inward/record.url?scp=84945302872&partnerID=8YFLogxK
U2 - 10.1016/j.asoc.2015.09.031
DO - 10.1016/j.asoc.2015.09.031
M3 - Article
AN - SCOPUS:84945302872
SN - 1568-4946
VL - 38
SP - 269
EP - 280
JO - Applied Soft Computing
JF - Applied Soft Computing
ER -