Improved and Scalable Online Learning of Spatial Concepts and Language Models with Mapping

Abstract

We propose a novel online learning algorithm, called SpCoSLAM 2.0, for spatial concepts and lexical acquisition with high accuracy and scalability. Previously, we proposed SpCoSLAM as an online learning algorithm based on unsupervised Bayesian probabilistic model that integrates multimodal place categorization, lexical acquisition, and SLAM. However, our original algorithm had limited estimation accuracy owing to the influence of the early stages of learning, and increased computational complexity with added training data. Therefore, we introduce techniques such as fixed-lag rejuvenation to reduce the calculation time while maintaining an accuracy higher than that of the original algorithm. The results show that, in terms of estimation accuracy, the proposed algorithm exceeds the original algorithm and is comparable to batch learning. In addition, the calculation time of the proposed algorithm does not depend on the amount of training data and becomes constant for each step of the scalable algorithm. Our approach will contribute to the realization of long-term spatial language interactions between humans and robots.

arXiv commentAccepted to Autonomous Robots (24 January 2020)

References in corpus (6)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• On Particle Methods for Parameter Estimation in State-Space Models
• Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks
• Symbol Emergence in Cognitive Developmental Systems: a Survey
• Online Spatial Concept and Lexical Acquisition with Simultaneous Localization and Mapping
• Spatial Concept Acquisition for a Mobile Robot that Integrates Self-Localization and Unsupervised Word Discovery from Spoken Sentences

Cited by in corpus (7)

• A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots
• Spatial Concept-Based Navigation with Human Speech Instructions via Probabilistic Inference on Bayesian Generative Model
• Online Deep Learning based on Auto-Encoder
• Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation
• Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discovery
• Hierarchical Path-planning from Speech Instructions with Spatial Concept-based Topometric Semantic Mapping
• On Parallelism in Music and Language: A Perspective from Symbol Emergence Systems based on Probabilistic Generative Models