Model driven programming of autonomous floats for multidisciplinary monitoring of the oceans

Abstract

Monitoring of the oceans with autonomous floats is of great interest for many disciplines. Monitoring on a global scale needs a multidisciplinary approach to be affordable. For this purpose, we propose an approach that allows oceanographers from different specialities to develop applications for autonomous floats. However, developing such applications usually requires expertise in embedded systems, and they must be reliable and efficient with regards to the limited resources of the floats (e.g., energy, processing power). We have followed a Model Driven Engineering approach composed of i) a Domain Specific Language to allow oceanographers to develop applications, ii) analysis tools to ensure that applications are efficient and reliable, iii) a composition tool to allow the deployment of different applications on a same float, and iv) a code generator that produce efficient and reliable code for the float. We present our approach with a biological and a seismological application. We validate it with technical metrics and an experiment.