Papers
3
Total Citations
8
H-Index
2
About
Katell Lagattu is a researcher at the forefront of autonomous underwater vehicle (AUV) safety and reliability, specializing in fault-tolerant control and state estimation. Her work addresses critical challenges in marine robotics, where unpredictable environments and actuator faults can compromise mission success. Lagattu’s most cited paper, “Experimental Validation of Ellipsoidal Techniques for State Estimation in Marine Applications” (2022, 5 citations), introduces a robust method for quantifying worst-case uncertainty in vessel localization—essential when GPS data is unreliable. She further advances the field with two 2025 papers on deep reinforcement learning (DRL) for actuator fault recovery: “Control Reallocation Using Deep Reinforcement Learning for Actuator Fault Recovery of an Autonomous Underwater Vehicle” (2 citations) and “Sim-to-Real Transfer for AUV Fault Control with Deep Reinforcement Learning” (1 citation). These works pioneer DRL-based control reallocation strategies that can adapt to faults in real-time, bridging the gap between simulation and real-world deployment. By combining theoretical rigor with practical validation, Lagattu’s research directly enhances the resilience of AUVs in hostile marine environments, making her a rising voice in maritime robotics and control systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3