Title: Mission Planning with Uncertain Models
Abstract: Mission planning for long-horizon tasks requires the planning agent to use a model to encode its interaction with its environment. In most robotic tasks some parts of this model are known with certainty, whereas other parts may only be known with uncertainty at design time, and must be updated via learning either between missions (“offline") or during execution (“online"). In this talk I’ll give a high-level summary of our recent work on mission planning with such uncertain models. This will range from planning in Markov decision processes (MDPs) with a Gaussian process prior over a single state features, to planning in uncertain MDPs and Bayes-adaptive MDPs where the true model cannot be known with certainty.
Bio: Nick Hawes is an Associate Professor of Robotics at the Oxford Robotics Institute. He researches Artificial Intelligence (AI) techniques for the creation of intelligent, autonomous robots that can work with or for humans. He has worked on long-term autonomy for mobile robots; information-processing architectures and software engineering for intelligent systems; the integration of AI planning techniques into a variety of robot systems; and the use of semantic and spatial knowledge to enable robots to reason about the possibilities for action in their worlds.
Nick Hawes completed a BSc (1999) and PhD (2004) in Artificial Intelligence at the University of Birmingham, before completing post-doctoral positions at MIT's Media Lab Europe in Dublin, and in the School of Computer Science at the University of Birmingham.