Episodic Memory Multimodal Learning for Robot Sensorimotor Map Building and Navigation

Chin, Wei Hong; Toda, Yuichiro; Kubota, Naoyuki; Loo, Chu Kiong; Seera, Manjeevan

doi:10.1109/tcds.2018.2875309

Cited by 11 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The source code of AutoCloud 1 , ASOINN 2 , SOINN+ 3 , TCA 4 , and CAEA 5 is provided by the authors of the original papers. The source code of CAE is available on GitHub 6 .…”

Section: Compared Algorithmsmentioning

confidence: 99%

“…Thus, these algorithms do not require any pre-defined parameters unlike k-means and SOM. Thanks to this feature, these algorithms are used as an information extraction method in unknown environments, such as simultaneous localization and mapping [6], and knowledge acquisition for robots [7]. However, GNG and SOINN tend to permanently and excessively generate nodes in their networks for memorizing new information, which may collapse learned information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Resonance Theory-Based Topological Clustering With a Divisive Hierarchical Structure Capable of Continual Learning

Masuyama¹,

Amako

Yuna

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Adaptive Resonance Theory (ART) is considered as an effective approach for realizing continual learning thanks to its ability to handle the plasticity-stability dilemma. In general, however, the clustering performance of ART-based algorithms strongly depends on the specification of a similarity threshold, i.e., a vigilance parameter, which is data-dependent and specified by hand. This paper proposes an ART-based topological clustering algorithm with a mechanism that automatically estimates a similarity threshold from the distribution of data points. In addition, for improving information extraction performance, a divisive hierarchical clustering algorithm capable of continual learning is proposed by introducing a hierarchical structure to the proposed algorithm. Experimental results demonstrate that the proposed algorithm has high clustering performance comparable with recently-proposed state-of-the-art hierarchical clustering algorithms.

show abstract

“…The source code of AutoCloud 1 , ASOINN 2 , SOINN+ 3 , TCA 4 , and CAEA 5 is provided by the authors of the original papers. The source code of CAE is available on GitHub 6 .…”

Section: Compared Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adaptive Resonance Theory-Based Topological Clustering With a Divisive Hierarchical Structure Capable of Continual Learning

Masuyama¹,

Amako

Yuna

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The cognitive map consists of a set of space coordinates that the robot has experienced and these nodes used to generate a global path. Chin et al [8] proposed an unsupervised learning model of episodic memory to categorize and encode experiences of a robot to the environment and generates a cognitive map.…”

Section: Introductionmentioning

confidence: 99%

Navigate to Remember: A Declarative Memory Model for Incremental Semantic Mapping

Chin

Kubota

et al. 2019

Intelligent Robotics and Applications

View full text Add to dashboard Cite

Biologically inspired computational techniques play a crucial role in robotic cognition. Artificial learning agents and robots that interact in complex environments must constantly acquire and refine knowledge over long periods of time. In this paper, we propose a novel recurrent neural architecture that mimics humans' declarative memory system for continuously generating a cognitive map during robot navigation. The proposed method termed as Declarative Memory Adaptive Recurrent Model (DM-ARM), and consists of three hierarchical memory courses: i) Working Memory, ii) Episodic Memory and iii) Semantic Memory layer. Each memory layer comprises a self-organizing adaptive recurrent incremental network (SOARIN) with a different learning task respectively. The Working Memory layer quickly clusters sensory information while the Episodic Memory layer learns fine-grained spatiotemporal relationships of clusters (temporal encoding). Both the memory layer learning is in an unsupervised manner. The Semantic Memory layer utilizes taskrelevant cues to adjust the level of architectural flexibility and generate a semantic map that contains more compact episodic representations. The effectiveness of the proposed recurrent neural architecture is evaluated through a series of experiments. We implemented and validated our proposed work on the tasks of robot navigation.

show abstract

A neurobiologically inspired mapping and navigating framework for mobile robots

et al. 2021

View full text Add to dashboard Cite

Episodic Memory Multimodal Learning for Robot Sensorimotor Map Building and Navigation

Cited by 11 publications

References 28 publications

Adaptive Resonance Theory-Based Topological Clustering With a Divisive Hierarchical Structure Capable of Continual Learning

Adaptive Resonance Theory-Based Topological Clustering With a Divisive Hierarchical Structure Capable of Continual Learning

Navigate to Remember: A Declarative Memory Model for Incremental Semantic Mapping

A neurobiologically inspired mapping and navigating framework for mobile robots

Contact Info

Product

Resources

About