6 papers
Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation
Mariela De Lucas Ãlvarez, Melvin Laux, Arthur de Freitas Precht +4
This work investigates uncertainty decomposition and explainability in a deep learning-based framework for gyroscope bias correction. A 1-D Convolutional Neural Network is trained…
Deep Reinforcement Learning for Spacecraft Attitude Control During Atmospheric Re-Entry
Alexander Fabisch, Melvin Laux, Mariela De Lucas Ãlvarez +2
Deep reinforcement learning has the potential to solve attitude control problems more adaptively, precisely, and robustly by handling nonlinear dynamics, uncertainties, and failure…
Contextual Multi-Task Reinforcement Learning for Autonomous Reef Monitoring
Melvin Laux, Yi-Ling Liu, Rina Alo +4
Although autonomous underwater vehicles promise the capability of marine ecosystem monitoring, their deployment is fundamentally limited by the difficulty of controlling vehicles u…
Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation
Yi-Ling Liu, Melvin Laux, Mariela De Lucas Alvarez +2
Autonomous underwater vehicles are required to perform multiple tasks adaptively and in an explainable manner under dynamic, uncertain conditions and limited sensing, challenges th…
DINO-Explorer: Active Underwater Discovery via Ego-Motion Compensated Semantic Predictive Coding
Yuhan Jin, Nayari Marie Lessa, Mariela De Lucas Alvarez +4
Marine ecosystem degradation necessitates continuous, scientifically selective underwater monitoring. However, most autonomous underwater vehicles (AUVs) operate as passive data lo…
Bayesian Inverse Physics for Neuro-Symbolic Robot Learning
Octavio Arriaga, Rebecca Adam, Melvin Laux +4
Real-world robotic applications, from autonomous exploration to assistive technologies, require adaptive, interpretable, and data-efficient learning paradigms. While deep learning…