Ioannis Rekleitis - SMSP Fall Seminar Series 2026

"Autonomous Field Robotics: Underwater Cave and Wreck Mapping and Environmental Monitoring"

Ioannis Rekleitis

Abstract: My research is focused on strategies for making robots operate autonomously in the real world even in the presence of adversarial conditions: low visibility, wind, currents, dynamic obstacles, confined environments, etc. The marine environment, below and above water, is the least studied on Earth and one of the most challenging. My work is focused on the coastal and inland areas where the vehicle needs to maneuver around obstacles, the environment dynamics present the most challenges, and autonomy is a key requirement.

This talk will start by addressing multi-robot exploration of shipwrecks and single-robot exploration of underwater caves. I will then discuss multi-sensor fusion for mapping shipwrecks, underwater caves, and coral reefs. Results on machine learning approaches for semantic mapping including coral classification and cave image segmentation will be discussed. Experimental results from several testing campaigns will be presented.