Home

My research focuses on explainable and active uncertainty quantification in Robotics and AI systems. I explore advanced mathematical and computational methods for inferring uncertainty in complex systems, bridging the gap between theoretical rigor and real-world deployment by addressing (i) the trade-off between approximation error and computational efficiency, (ii) the integration of physics-informed and learning-based inference approaches, and (iii) the balance between first-principles reasoning and engineering practicality. 

My research aims to develop robust and scalable uncertainty-aware robotic systems, capable of generalizable and intelligent operation across complex and unstructured environments. I address key challenges in robotic perception and navigation through the lens of uncertainty quantification, focusing on multi-modal sensor fusion, uncertainty-aware decision-making from perception to planning, and achieving reliable long-term operation in large-scale environments. 

To achieve this, I integrate interdisciplinary approaches in approximate Bayesian inference/filtering, probabilistic estimation theory, control theory, nonlinear optimization, information geometry, and statistical/machine learning techniques, unifying insights across these domains.