Paulo Padrao

Ph.D. Candidate


Lecture Information:
  • October 24, 2023
  • 11:00 AM
  • CASE 349 & Zoom
Headshot of Paulo Padrao

Speaker Bio

Paulo Padrao is currently a research assistant at the Knight Foundation School of Computing and Information Sciences at Florida International University. His interests are primarily related to autonomous robots, artificial intelligence, and engineering education. He received his master’s degree in electrical engineering (control, automation & robotics) from the University of Rio de Janeiro, Brazil. Before joining FIU, Paulo served as a STEM instructor for six years at Instituto Federal Fluminense, Brazil, where he delivered a total of 12 courses to hundreds of undergraduate students. He was also a visiting student at Santa Clara University (2012/2013), Stanford University (2013), the University of Duisburg-Essen, Germany (2015), and research intern at the German Aerospace Center (2018). During his doctoral studies, Paulo has published 6 peer-reviewed papers and served as a graduate research mentor for the NSF-sponsored Research Experience for Teachers (RET) program for three consecutive years, a facilitator for FIU’s Artificial Intelligence Micro-Credential (2022, 2023), and a reviewer for peer-reviewed conferences and journals such as IEEE Sensors and IEEE ICRA (2021, 2022, 2023).

Abstract

There has been significant attention on the usefulness and application of intelligent autonomous systems (IAS), including underwater and surface vehicles (AUVs and ASVs), for continuous monitoring of aquatic environments. These vehicles have enabled various research studies, including the examination of physical phenomena (e.g. temperature fluctuations, salinity levels, and the emergence of harmful algae blooms), offshore infrastructure inspection and maintenance, and environmental monitoring and restoration. Given the spatial-temporal variability of the marine environment and its communication-constrained nature, underwater localization is often limited, necessitating the use of state estimation models to minimize uncertainties and enhance decision-making. In addition to that, experimental validation and testing of algorithms in aquatic environments are costly endeavors. Therefore, the utilization of high-fidelity simulators and scaled-down versions of the platforms will serve as essential tools to mitigate the logistical challenges associated with deploying robots in real underwater environments. These resources will enable us to conduct rigorous testing, refine algorithms, and optimize performance in a controlled and cost-effective manner. Also, working in the underwater environment is unnatural for humans, often requiring the teleoperation of underwater robots. In this context, the design of human-robot interfaces that comply with user comfort and efficiency constraints plays a major role in enabling a wide range of applications and fields of research. The primary objectives of this proposal are to address the theoretical and technical challenges associated with creating a comprehensive framework for autonomous sampling, localization, navigation, and human-robot collaboration in dynamic marine environments. To achieve these objectives, we propose a research agenda that will be focused on four research topics: (1) State Estimation in Environments with Extreme Sensing and Communication Constraints; (2) Sim-to-Scale-to-Real for Heterogeneous Autonomous Systems in Marine Environments; (3) Optimal Human-Robot Interface Design; and (4) Experimental Validation and Testing.