Self-Organizing Incremental Associative Memory-Based Robot Navigation

Sirinart TANGRUAMSUB; Aram KAWEWONG; Manabu TSUBOYAMA; Osamu HASEGAWA

doi:10.1587/transinf.E95.D.2415

Self-Organizing Incremental Associative Memory-Based Robot Navigation

Sirinart TANGRUAMSUB, Aram KAWEWONG, Manabu TSUBOYAMA, Osamu HASEGAWA

Full Text Views

0

Share
Cite this

Summary :

This paper presents a new incremental approach for robot navigation using associative memory. We defined the association as node→action→node where node is the robot position and action is the action of a robot (i.e., orientation, direction). These associations are used for path planning by retrieving a sequence of path fragments (in form of (node→action→node) → (node→action→node) →…) starting from the start point to the goal. To learn such associations, we applied the associative memory using Self-Organizing Incremental Associative Memory (SOIAM). Our proposed method comprises three layers: input layer, memory layer and associative layer. The input layer is used for collecting input observations. The memory layer clusters the obtained observations into a set of topological nodes incrementally. In the associative layer, the associative memory is used as the topological map where nodes are associated with actions. The advantages of our method are that 1) it does not need prior knowledge, 2) it can process data in continuous space which is very important for real-world robot navigation and 3) it can learn in an incremental unsupervised manner. Experiments are done with a realistic robot simulator: Webots. We divided the experiments into 4 parts to show the ability of creating a map, incremental learning and symbol-based recognition. Results show that our method offers a 90% success rate for reaching the goal.

Publication: IEICE TRANSACTIONS on Information Vol.E95-D No.10 pp.2415-2425

Publication Date: 2012/10/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E95.D.2415

Type of Manuscript: PAPER

Category: Information Network

Cite this

Copy

Sirinart TANGRUAMSUB, Aram KAWEWONG, Manabu TSUBOYAMA, Osamu HASEGAWA, "Self-Organizing Incremental Associative Memory-Based Robot Navigation" in IEICE TRANSACTIONS on Information, vol. E95-D, no. 10, pp. 2415-2425, October 2012, doi: 10.1587/transinf.E95.D.2415.
Abstract: This paper presents a new incremental approach for robot navigation using associative memory. We defined the association as node→action→node where node is the robot position and action is the action of a robot (i.e., orientation, direction). These associations are used for path planning by retrieving a sequence of path fragments (in form of (node→action→node) → (node→action→node) →…) starting from the start point to the goal. To learn such associations, we applied the associative memory using Self-Organizing Incremental Associative Memory (SOIAM). Our proposed method comprises three layers: input layer, memory layer and associative layer. The input layer is used for collecting input observations. The memory layer clusters the obtained observations into a set of topological nodes incrementally. In the associative layer, the associative memory is used as the topological map where nodes are associated with actions. The advantages of our method are that 1) it does not need prior knowledge, 2) it can process data in continuous space which is very important for real-world robot navigation and 3) it can learn in an incremental unsupervised manner. Experiments are done with a realistic robot simulator: Webots. We divided the experiments into 4 parts to show the ability of creating a map, incremental learning and symbol-based recognition. Results show that our method offers a 90% success rate for reaching the goal.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E95.D.2415/_p

Copy

@ARTICLE{e95-d_10_2415,
author={Sirinart TANGRUAMSUB, Aram KAWEWONG, Manabu TSUBOYAMA, Osamu HASEGAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Self-Organizing Incremental Associative Memory-Based Robot Navigation},
year={2012},
volume={E95-D},
number={10},
pages={2415-2425},
abstract={This paper presents a new incremental approach for robot navigation using associative memory. We defined the association as node→action→node where node is the robot position and action is the action of a robot (i.e., orientation, direction). These associations are used for path planning by retrieving a sequence of path fragments (in form of (node→action→node) → (node→action→node) →…) starting from the start point to the goal. To learn such associations, we applied the associative memory using Self-Organizing Incremental Associative Memory (SOIAM). Our proposed method comprises three layers: input layer, memory layer and associative layer. The input layer is used for collecting input observations. The memory layer clusters the obtained observations into a set of topological nodes incrementally. In the associative layer, the associative memory is used as the topological map where nodes are associated with actions. The advantages of our method are that 1) it does not need prior knowledge, 2) it can process data in continuous space which is very important for real-world robot navigation and 3) it can learn in an incremental unsupervised manner. Experiments are done with a realistic robot simulator: Webots. We divided the experiments into 4 parts to show the ability of creating a map, incremental learning and symbol-based recognition. Results show that our method offers a 90% success rate for reaching the goal.},
keywords={},
doi={10.1587/transinf.E95.D.2415},
ISSN={1745-1361},
month={October},}

Copy

TY - JOUR
TI - Self-Organizing Incremental Associative Memory-Based Robot Navigation
T2 - IEICE TRANSACTIONS on Information
SP - 2415
EP - 2425
AU - Sirinart TANGRUAMSUB
AU - Aram KAWEWONG
AU - Manabu TSUBOYAMA
AU - Osamu HASEGAWA
PY - 2012
DO - 10.1587/transinf.E95.D.2415
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2012
AB - This paper presents a new incremental approach for robot navigation using associative memory. We defined the association as node→action→node where node is the robot position and action is the action of a robot (i.e., orientation, direction). These associations are used for path planning by retrieving a sequence of path fragments (in form of (node→action→node) → (node→action→node) →…) starting from the start point to the goal. To learn such associations, we applied the associative memory using Self-Organizing Incremental Associative Memory (SOIAM). Our proposed method comprises three layers: input layer, memory layer and associative layer. The input layer is used for collecting input observations. The memory layer clusters the obtained observations into a set of topological nodes incrementally. In the associative layer, the associative memory is used as the topological map where nodes are associated with actions. The advantages of our method are that 1) it does not need prior knowledge, 2) it can process data in continuous space which is very important for real-world robot navigation and 3) it can learn in an incremental unsupervised manner. Experiments are done with a realistic robot simulator: Webots. We divided the experiments into 4 parts to show the ability of creating a map, incremental learning and symbol-based recognition. Results show that our method offers a 90% success rate for reaching the goal.
ER -