My primary research interest lies in ensuring robot safety when integrating AI-driven decision making, in addition to robot control and design. 

As AI becomes increasingly embedded in robotic systems, ensuring safe behavior under uncertainty is critical. However, while much attention is given to improving AI performance, safety is often treated as an afterthought. I believe safety should be treated as a first-class objective, with statistical guarantees that systems will behave reliably—even in uncertain or novel situations.