Projects

Partial observability is fundamental to our uncertain world, and we need to reason about it while making decisions. Partially Observable Markov Decision Processes (POMDP) presents a principled approach to model sequential decision-making problems for partially observable domains.

Natural language has the potential to be a powerful interface for communication in human-robot interaction. Robots can be trained to retrieve objects with unconstrained natural language expressions. To do so, the robot needs to ground the object from the semantic and spatial information provided in the referring expression.