Abstract
Flash floods are one of the most common natural disasters worldwide, causing thousands of casualties every year. A combination of fixed and mobile sensors can be used to track these events. In particular, the emergence of Unmanned Aerial Vehicles (UAVs) could enable the monitoring of floods over large geographical areas. In this talk, we focus on the problems of sensing, data assimilation, and trajectory planning for a swarm of mobile agents (for example UAVs) sensing floods We first show that deep-learning can efficiently approximate the flood evolution over time, given external model inputs. We then formulate the problem of maximizing the information gained over a finite time horizon, and solve it to determine optimal UAV trajectories. We then illustrate the data assimilation process.
Brief Biography
Christian Claudel is an Associate Professor of Civil, Architectural and Environmental Engineering at UT-Austin. He received the PhD degree in Electrical Engineering from UC-Berkeley in 2010, and the MS degree in Plasma Physics from Ecole Normale Superieure de Lyon in 2004. He received the Leon Chua Award from UC-Berkeley in 2010 for his work on the Mobile Millennium traffic monitoring system. His research interests include control and estimation of distributed parameter systems, wireless sensor networks and unmanned aerial vehicles.