Position Estimation, Planning, and Learning with Partially Observable Markov Models

I am particularly interested in making Xavier and Amelia navigate autonomously and robustly in corridor environments. This includes work on position estimation, planning, plan monitoring, and learning. My work shows that one can build a whole robot architecture around Partially Observable Markov Decision Process (POMDP) models. POMDP models allow the robots to account for actuator and sensor uncertainty and to integrate topological map information with approximate metric information. They also allow the robots to act and learn even if they are uncertain about their current location.

Relevant publications:

Unsupervised Learning of Probabilistic Models for Robot Navigation, ICRA 1996.
Modeling Risk and Soft Deadlines for Robot Navigation, AAAI Spring 1996.
Robot Navigation with Markov Models, RUR 1995.
Probabilistic Robot Navigation in Partially Observable Environments, IJCAI 1995.

Check out my home page and my other projects!

Sven Koenig

skoenig+@cs.cmu.edu / Last update: January 1 1996