SpCoSLAM 2.0: An Improved and Scalable Online Learning of Spatial Concepts and Language Models with Mapping

In this paper, we propose a novel online learning algorithm, SpCoSLAM 2.0 for spatial concepts and lexical acquisition with higher accuracy and scalability. In previous work, we proposed SpCoSLAM as an online learning algorithm based on the Rao–Blackwellized particle filter. However, this conventional algorithm had problems such as the decrease of the estimation accuracy due to the influence of the early stages of learning as well as the increase of the computational complexity with the increase of the training data. Therefore, we first develop an improved algorithm by introducing new techniques such as rejuvenation. Next, we develop a scalable algorithm to reduce the calculation time while maintaining a higher accuracy than the conventional algorithm. In the experiment, we evaluate and compare the estimation accuracy and calculation time of the proposed algorithm, conventional online algorithm, and batch learning. The experimental results demonstrate that the proposed algorithm not only exceeds the accuracy of the conventional algorithm but also capable of achieving an accuracy comparable to that of batch learning. In addition, the proposed algorithm showed that the calculation time does not depend on the amount of training data and becomes constant for each step with the scalable algorithm.