Research


Deep Learning & Optimal Control: what's the connection?

DL and OC are mutually influencing each other in scientific research nowadays. Can we use control theory to improve the training of DNN? Can we use DL to improve classical numerical algorithms?
Further reading

Path-planning with uncertainty: a simple model

Where should a planner wait if a list of possible targets are known(instead of a single deterministic one)? What if information can be obtained gradually? Can the planner make robust plans?
Further reading

Resolving numerical artifacts in Eikonal solvers

Why do some computed optimal paths show numerical artifacts? How to develop a scheme to make them disappear?
Further reading