Application of Optimization Algorithms to Trajectory Planning for Underwater Gliders Jos´ e Isern-Gonz´ alez, Daniel Hern´ andez-Sosa, Enrique Fern´andez-Perdomo, Jorge Cabrera-G´amez, Antonio C. Dom´ ınguez-Brito, and V´ ıctor Prieto-Mara˜ n´on University Institute of Sistemas Inteligentes y Aplicaciones Num´ ericas en Ingenier´ ıa Universidad de Las Palmas de Gran Canaria - 35017, Las Palmas, Spain {jisern,dhernandez,efernandez,jcabrera,adominguez}@iusiani.ulpgc.es, vprieto@ono.com Abstract. Underwater gliders are a technology that have demonstrated to be a valid tool for diverse applications in the oceans including valida- tion of currents models, environmental control or security. Due to their low speed, gliders might drift significantly from the planned trajectory by effect of ocean currents, making path planning a crucial tool for them. In this work, we present a novel path planning scheme for this kind of un- derwater agents based on optimization techniques that shows promising results on realistic simulations, including highly time-varying ocean cur- rents. This method models the glider as an intelligent agent that senses the ocean currents speed and direction, and generates an path according to the predefined objectives. The proposal reflects accurately the physi- cal vehicle motion pattern and can be easily configured and adapted to various optimization problems regarding underwater vehicles’ missions. This method gives a superior performance when is compared with other approaches. Keywords: underwater gliders, path planning. 1 Introduction Underwater gliders constitute a technology that is being used in a wide variety of applications in oceanography and survey (inspection) mission because they allow to carry out long missions with low power consumption. A glider is Autonomous Underwater Vehicle (AUV) that operates modifying its buoyancy in a cyclic pattern. These changes produce vertical impulsion that is transformed into horizontal speed by effect of wings and tail. The result is a continuous climb and dive displacement (Fig. 1). These cycles are repeated typically for 6-12 hours periods, returning then the vehicle to surface for sending status and data communication to control room, as well as, receiving new orders, commonly the next way-point or bearing. After 15-30 minutes in surface, the next immersion period, also referred as stint, is started again. As gliders do not communicate while they are submerged, the on-board navigation system simply tries to keep the last commanded bearing during the whole stint. R. Moreno-D´ ıaz et al. (Eds.): EUROCAST 2011, Part II, LNCS 6928, pp. 433–440, 2012. c  Springer-Verlag Berlin Heidelberg 2012