R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...
Recent research in robot exploration and mapping has focused on sampling environmental hotspot fields. This exploration task is formalized by Low, Dolan, and Khosla (2008) in a se...
This paper presents a simple and efficient method of modeling synthetic vision, memory, and learning for autonomous animated characters in real-time virtual environments. The mode...
This paper presents a monocular vision framework enabling feature-oriented appearance-based navigation in large outdoor environments containing other moving objects. The framework ...
Sinisa Segvic, Anthony Remazeilles, Albert Diosi, ...
This paper investigates safe and efficient map-building strategies for a mobile robot with imperfect control and sensing. In the implementation, a robot equipped with a range sens...