Abstract
This paper briefly presents the main points on the development and testing of an extremum seeking controller used to maximize the longitudinal velocity of surface sailing vehicles by changing the angle of the sail. The algorithm is suitable for sailing purposes since it requires only the measurements of the vehicle's velocity and the sail angle. As an illustration, we present a few simulation results on our previously-obtained sailing yacht simulator, which was developed based on a 4 DOF nonlinear dynamic model for surface sailing vehicles, showing that the proposed extremum seeking controller is capable of maximizing the sailing yacht's speed performance through online sail tuning. Furthermore, the proposed sail optimization algorithm is tested at sea on an experimental platform, i.e. a small scale autonomous sailboat, illustrating the potential of the controller.

Abstract
Sailing has been for long times the only means of ship propulsion at sea. Although the performance of a sailing vessel is well below the present power driven ships, either in terms of navigation speed and predictability, wind energy is absolutely renewable, clean and free. Unmanned autonomous sailing boats may exhibit a virtually unlimited autonomy and be able to perform unassisted missions at sea for long periods of time. Promising applications include oceanographic and weather data collecting, surveillance and even military applications. The Microtransat competition, launched in Europe in 2006, has been a key initiative to promote the development of robotic unmanned sailing boats. Various regattas have taken place across Europe and the ultimate challenge will be a transatlantic race. This paper presents an autonomous sailing boat developed at the University of Porto, Portugal, with emphasis on the hardware and software computing infrastructure. This platform is capable of carrying a few kilograms of sensing equipment that can be hooked to the boat's main computer, also providing support for short and long range data communications.

Abstract
Autonomous sailboats are robotic vessels that use wind energy for propulsion and control the sails and rudders without human intervention. The use of autonomous sailboats for ocean sampling has been tentatively proposed before, but there have been minor efforts towards the development and deployment of actual prototypes, due to a number of technical limitations and significant risks of operation. Currently, most of the limitations have been surpassed, with the availability of extremely low power electronics, flexible computational systems, reliable communication devices and high performance renewable power sources. At the same time, some of the major risks have been mitigated, allowing this emerging technology to become an effective tool for a wide range of applications in real scenarios. We illustrate some of these scenarios and we describe the status of the current efforts being made to develop operational prototypes.

Abstract
This paper presents the computing infrastructure used in an autonomous unmanned small-scale sailboat. The system is based on a FPGA and includes custom designed interfaces for the various sensors and actuators used in the sailboat. The central processing unit is a 32-bit 50 MHz RISC microprocessor implemented as a soft IP core in the FPGA. The computing system runs uClinux, a simplified version of the popular Linux operating system. The usage of a reconfigurable platform enables a quick reconfiguration of the logic circuit implemented in the FPGA, facilitating the development stage and allowing a dynamic switch among different implementations, according to the navigation requirements and environmental conditions.

Abstract
This paper presents an embedded hardware/software implementation for the computing system of a small scale unmanned autonomous sailing boat. The system is integrated in a single XILINX FPGA, and hosts a Microblaze soft processor surrounded with heterogeneous, custom designed, control and processing modules than handle the interface with all the sensors, actuators and communication devices of the sailing boat. These interfacing modules implement tasks that have been decentralized from the main processor, thus alleviating its computational load and providing processing time for higher level software applications. Using an FPGA to implement an integrated single-chip computing system, as an alternative to conventional processors, has proven to be a very flexible solution as it eases the migration of computation tasks between the hardware and software domains, and more importantly, allowing the rapid adaptation of the digital interfacing hardware in order to support additional peripheral devices required for an application mission. The software component of the boat's control system runs on the top of the uClinux embedded operating system and is formed by various concurrent applications developed in C with the standard Linux libraries. The remote monitoring, configuration and operation of the sailing boat is done via a WiFi link, using a graphics interactive application that runs on a conventional PC.

Abstract
This paper addresses the design and implementation of feedback controllers for the direction of autonomous robotic sailboats. In order to design such a controller, it is important to determine a model for the sailboat dynamics during turns. However, there are many uncontrollable factors that may affect the direction of the sailboat, which make it difficult to obtain an accurate model and require a lot of sensors to feed a proper controller. Instead, we assume a rather simple model relating the most important variables and concentrate on data that can easily be available with simple low-cost sensors, compensating the lack of accuracy of the model with the robustness of the controller. We describe our approach to extract the parameters of such a dynamic model using data obtained in field experiments and we show how to use this model to tune a PI controller. As a case study, we use the FASt vehicle, a 2.5 m long robotic sailing boat capable of fully autonomous navigation through a set of predefined marks. Experimental results show the performance of the designed controller. © 2010 IEEE.