Lucas M. Longaray

Papers

Total Citations

H-Index

About

Lucas M. Longaray is a researcher specializing in underwater robotics, with a focus on simultaneous localization and mapping (SLAM) and place recognition in challenging subsea environments. His work addresses the critical problem of autonomous navigation in turbid waters, where traditional optical sensors fail. Longaray’s most-cited paper, “Towards comparison of underwater SLAM methods: An open dataset collection” (2016, 21 citations), introduced a pioneering open-source benchmark using simulated datasets from the Underwater Simulator (UWSim). This resource allows researchers to evaluate SLAM algorithms under controlled turbidity levels, providing ground truth trajectories and multi-sensor data—a foundational contribution to reproducible underwater robotics research. In his equally cited work, “Underwater Place Recognition in Unknown Environments with Triplet Based Acoustic Image Retrieval” (2018, 21 citations), Longaray advanced the use of forward-looking sonars (FLS) for perception. He developed a triplet-based deep learning method to retrieve acoustic images for place recognition, enabling Remotely Operated Vehicles (ROVs) to navigate and map regions without prior knowledge. By leveraging sonar imagery unaffected by turbidity, Longaray’s research bridges a critical gap in autonomous underwater operations, offering robust solutions for exploration and mapping in visually degraded environments.