Abstract

Abstract
This work addresses the coordinated operation of an autonomous underwater vehicle and an autonomous surface vessel and its main goal is the development of an infrastructure that allows the surface vessel to dynamically position itself above the underwater vehicle while the later one is collecting data and navigating in long baseline mode using a set of beacons installed in the operation area. Besides a formal statement of the coordination problem, we present results both from real experiments and from simulations that illustrate the proposed solution.

Abstract

Abstract
This paper describes a Synthetic Aperture Sonar (SAS) system being developed at the University of Porto to be used in a small autonomous boat for the survey of shallow water environments, such as rivers, deltas, estuaries and dams. Its purpose is to obtain high resolution echo reflectivity maps through synthetic aperture techniques, taking advantage of the high precision navigation system of the boat. In the future the production of bottom tomography maps is also considered through the use of interferometric imaging techniques.

Abstract

Abstract
In this paper we study the problem of constructing histograms from high-speed time-changing data streams. Learning in this context requires the ability to process examples once at the rate they arrive, maintaining a histogram consistent with the most recent data, and forgetting out-date data whenever a change in the distribution is detected. To construct histogram from high-speed data streams we use the two layer structure used in the Partition Incremental Discretization (PiD) algorithm. Our contribution is a new method to detect whenever a change in the distribution generating examples occurs. The base idea consists of monitoring distributions from two different time windows: the reference time window, that reflects the distribution observed in the past; and the current time window reflecting the distribution observed in the most recent data. We compare both distributions and signal a change whenever they are greater than a threshold value, using three different methods: the Entropy Absolute Difference, the Kullback-Leibler divergence and the Cosine Distance. The experimental results suggest that Kullback-Leibler divergence exhibit high probability in change detection, faster detection rates, with few false positives alarms.