Unsupervised Temporospatial Neural Architecture for Sensorimotor Map Learning

Abstract

The ability to learn the sensorimotor maps of unknown environments without supervision is a vital capability of any autonomous agent, be it biological or artificial. An accurate sensorimotor map should be able to encode the agent’s world and equip it with the capability to anticipate or predict the results of its actions. However, to design a robust autonomous learning technique for an unknown, dynamic, partially observable, or noisy environment remains a daunting task. This article proposes a temporospatial merge grow when required (TMGWR) network for continuous self-organization of an agent’s sensorimotor awareness in noisy environments. TMGWR is an adaptive neural algorithm that learns the sensorimotor map of an agent’s world using a time series self-organizing strategy and the grow when required (GWR) algorithm. The algorithm is compared with growing neural gas (GNG), GWR, and time GNG in terms of their disambiguation performance, sensorial representation accuracy, and sensorimotor-link error, a new metric that is developed in this article to evaluate how well a sensorimotor map represents causality in the agent’s world. The outcomes of the experiments show that TMGWR is more efficient and suitable for sensorimotor map learning in noisy environments than the competing algorithms.