Vision-based topological mapping and Navigation with self-organizing neural networks

Spatial mapping and navigation are critical cognitive functions of autonomous agents, enabling one to learn an internal representation of an environment and move through space with real-time sensory inputs, such as visual observations. Existing models for vision-based mapping and navigation, however...

Full description

Saved in:
Bibliographic Details
Main Authors: HU, Yue, SUBAGDJA, Budhitama, TAN, Ah-hwee
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6049
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-7052
record_format dspace
spelling sg-smu-ink.sis_research-70522021-08-03T09:01:41Z Vision-based topological mapping and Navigation with self-organizing neural networks HU, Yue SUBAGDJA, Budhitama TAN, Ah-hwee Spatial mapping and navigation are critical cognitive functions of autonomous agents, enabling one to learn an internal representation of an environment and move through space with real-time sensory inputs, such as visual observations. Existing models for vision-based mapping and navigation, however, suffer from memory requirements that increase linearly with exploration duration and indirect path following behaviors. This article presents e-TM, a self-organizing neural network-based framework for incremental topological mapping and navigation. e-TM models the exploration trajectories explicitly as episodic memory, wherein salient landmarks are sequentially extracted as ``events'' from streaming observations. A memory consolidation procedure then performs a playback mechanism and transfers the embedded knowledge of the environmental layout into spatial memory, encoding topological relations between landmarks. Fusion adaptive resonance theory (ART) networks, as the building block of the two memory modules, can generalize multiple input patterns into memory templates and, therefore, provide a compact spatial representation and support the discovery of novel shortcuts through inferences. For navigation, e-TM applies a transfer learning paradigm to integrate human demonstrations into a pretrained locomotion network for smoother movements. Experimental results based on VizDoom, a simulated 3-D environment, have shown that, compared to semiparametric topological memory (SPTM), a state-of-the-art model, e-TM reduces the time costs of navigation significantly while learning much sparser topological graphs. 2021-06-01T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/6049 info:doi/10.1109/TNNLS.2021.3084212 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems OS and Networks
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
OS and Networks
spellingShingle Databases and Information Systems
OS and Networks
HU, Yue
SUBAGDJA, Budhitama
TAN, Ah-hwee
Vision-based topological mapping and Navigation with self-organizing neural networks
description Spatial mapping and navigation are critical cognitive functions of autonomous agents, enabling one to learn an internal representation of an environment and move through space with real-time sensory inputs, such as visual observations. Existing models for vision-based mapping and navigation, however, suffer from memory requirements that increase linearly with exploration duration and indirect path following behaviors. This article presents e-TM, a self-organizing neural network-based framework for incremental topological mapping and navigation. e-TM models the exploration trajectories explicitly as episodic memory, wherein salient landmarks are sequentially extracted as ``events'' from streaming observations. A memory consolidation procedure then performs a playback mechanism and transfers the embedded knowledge of the environmental layout into spatial memory, encoding topological relations between landmarks. Fusion adaptive resonance theory (ART) networks, as the building block of the two memory modules, can generalize multiple input patterns into memory templates and, therefore, provide a compact spatial representation and support the discovery of novel shortcuts through inferences. For navigation, e-TM applies a transfer learning paradigm to integrate human demonstrations into a pretrained locomotion network for smoother movements. Experimental results based on VizDoom, a simulated 3-D environment, have shown that, compared to semiparametric topological memory (SPTM), a state-of-the-art model, e-TM reduces the time costs of navigation significantly while learning much sparser topological graphs.
format text
author HU, Yue
SUBAGDJA, Budhitama
TAN, Ah-hwee
author_facet HU, Yue
SUBAGDJA, Budhitama
TAN, Ah-hwee
author_sort HU, Yue
title Vision-based topological mapping and Navigation with self-organizing neural networks
title_short Vision-based topological mapping and Navigation with self-organizing neural networks
title_full Vision-based topological mapping and Navigation with self-organizing neural networks
title_fullStr Vision-based topological mapping and Navigation with self-organizing neural networks
title_full_unstemmed Vision-based topological mapping and Navigation with self-organizing neural networks
title_sort vision-based topological mapping and navigation with self-organizing neural networks
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/6049
_version_ 1770575773888937984