Project "Agent Architectures for Coping with Uncertainty"
(scroll down for publications)

Autonomous agents need to generate plans that achieve their goals even if they are never sure what their current state is. For example, the actuator and sensor uncertainty of mobile robots prevents them from knowing their exact location during navigation. Consequently, we have designed agent architectures that are able to cope with a substantial amount of uncertainty. One of these agent architectures - developed as part of our dissertation - is based on partially observable Markov decision processes models (POMDP) from operations research. This agent architecture is part of Xavier, a mobile robot at Carnegie Mellon University that received navigation requests from users worldwide via the World Wide Web and has traveled more than 230 kilometers.

Representative Publications

• O. Walker, F. Vanegas, F. Gonzalez and S. Koenig. A Deep Reinforcement Learning Framework for UAV Navigation in Indoor Environments. In IEEE Aerospace Conference (AeroConf), 2019. [downloadable]
  

• A. Atrash and S. Koenig. Probabilistic Planning for Behavior-Based Robots. In International FLAIRS Conference (FLAIRS), 531-535, 2001. [downloadable]
  

• R. Simmons, J. Fernandez, R. Goodwin, S. Koenig and J. O'Sullivan. Lessons Learned from Xavier. IEEE Robotics and Automation Magazine, 7, (2), 33-39, 2000. [downloadable]
  

• S. Koenig and R.G. Simmons. Xavier: A Robot Navigation Architecture Based on Partially Observable Markov Decision Process Models. In Artificial Intelligence Based Mobile Robotics: Case Studies of Successful Robot Systems, D. Kortenkamp, R. Bonasso and R. Murphy (editor), 91-122. MIT Press, 1998. [downloadable]
  

• R.G. Simmons, R. Goodwin, K. Haigh, S. Koenig and J. O'Sullivan. Xavier: Experience with a Layered Robot Architecture. Sigart Bulletin, 8, (1-4), 22-33, 1997. [downloadable]
  

• S. Koenig, R. Goodwin and R.G. Simmons. Robot Navigation with Markov Models: A Framework for Path Planning and Learning with Limited Computational Resources. In Reasoning with Uncertainty in Robotics, L. Dorst, M. van Lambalgen and R. Voorbraak (editor), volume 1093 of Lecture Notes in Artificial Intelligence , 322-337. Springer, 1996. [downloadable]
  

• R. Simmons, S. Thrun, G. Armstrong, R. Goodwin, K. Haigh, S. Koenig, S. Mahamud, D. Nikovski and J. O'Sullivan. Amelia [Robot Competition Abstract]. In AAAI Conference on Artificial Intelligence (AAAI), 1368, 1996. [downloadable]
  

• S. Koenig and R.G. Simmons. Passive Distance Learning for Robot Navigation. In International Conference on Machine Learning (ICML), 266-274, 1996. [downloadable]
  

• S. Koenig and R.G. Simmons. Unsupervised Learning of Probabilistic Models for Robot Navigation. In International Conference on Robotics and Automation (ICRA), 2301-2308, 1996. [downloadable]
  

• R. Simmons and S. Koenig. Probabilistic Robot Navigation in Partially Observable Environments. In International Joint Conference on Artificial Intelligence (IJCAI), 1080-1087, 1995. [downloadable]
  

Many publishers do not want authors to make their papers available electronically after the papers have been published. Please use the electronic versions provided here only if hardcopies are not yet available. If you have comments on any of these papers, please send me an email! Also, please send me your papers if we have common interests.

This page was automatically created by a bibliography maintenance system that was developed as part of an undergraduate research project, advised by Sven Koenig.

Home Page of Sven Koenig