In our research we study rational agents which learn how to choose the best conditional, partial plan in any situation. The agent uses an incomplete symbolic inference engine, emp...
Abstract— We present an approach for the dynamic assignment and reassignment of a large team of homogeneous robotic agents to multiple locations with applications to search and r...
For many machine learning solutions to complex applications, there are significant performance advantages to decomposing the overall task into several simpler sequential stages, c...
Self-localisation is an essential competence for mobile robot navigation. Due to the fundamental unreliability of dead reckoning, a robot must depend on its perception of external...
Mixed-initiativesystemspresent the challengeof finding an effective level of interaction betweenhumans and computers. Machinelearning presents a promising approachto this problemi...