Autonomous Data Collection Using a Self-Organizing Map

The self-organizing map (SOM) is an unsupervised learning technique providing a transformation of a high-dimensional input space into a lower dimensional output space. In this paper, we utilize the SOM for the traveling salesman problem (TSP) to develop a solution to autonomous data collection. Autonomous data collection requires gathering data from predeployed sensors by moving within a limited communication radius. We propose a new growing SOM that adapts the number of neurons during learning, which also allows our approach to apply in cases where some sensors can be ignored due to a lower priority. Based on a comparison with available combinatorial heuristic algorithms for relevant variants of the TSP, the proposed approach demonstrates improved results, while also being less computationally demanding. Moreover, the proposed learning procedure can be extended to cases where particular sensors have varying communication radii, and it can also be extended to multivehicle planning.

I. Introduction

The problem addressed in this paper is motivated by environmental monitoring and surveillance scenarios, where an autonomous vehicle is required to collect data from predeployed sensors. Examples include autonomous underwater vehicles (AUVs) assisting oceanographers to track harmful algae blooms [1], aerial vehicles collecting data about changing ecosystems [2], and ground vehicles monitoring volcanic activity [3]. In particular, the proposed approach aims to provide an efficient solution to autonomous data collection from sensors placed on an ocean floor [4]. A convenient method for data collection is to equip each sensor with wireless communication capability and retrieve data remotely. However, due to limited communication technology available in the underwater domain (e.g., wireless acoustic modems), a mobile underwater vehicle is needed to retrieve the data from deployed sensors [5].