Machine Learning and Robotics
Greg Grudic, Jane Mulligan, Michael Otte, and Adam Bates. Online learning of multiple perceptual models for navigation in unknown terrain, 6th International Conference on Field and Service Robotics, 2007. (pdf)
Michael J. Procopio, Jane Mulligan, and Greg Grudic. Long-term learning using multiple models for outdoor autonomous robot navigation, 2007 IEEE International Conference on Intelligent Robots and Systems, 2007. (pdf)
Path Planning in Image Space
Michael Otte, Scott Richardson, Greg Grudic, and Jane Mulligan. Local path planning in image space for autonomous robot navigation in unstructured environments, 2007 IEEE International Conference on Intelligent Robots and Systems, 2007. (pdf)
Topological Maps and Visual Manifolds
Greg Grudic and Jane Mulligan, Outdoor Path Labeling Using Polynomial Mahalanobis Distance, Robotics: Science and Systems II, 2006. (pdf) (code) (MPG Video showing obstacle detection in the far field without stereo)
Jane Mulligan and Greg Grudic, Topological Mapping from Image Sequences. In Proceedings of the IEEE Workshop on Learning in Computer Vision and Pattern Recognition (with CVPR05), 2005. (pdf)
Greg Grudic and Jane Mulligan, Topological mapping with multiple visual manifolds., In Robotics: Science and Systems I, 2005. (pdf)
Clustering And Semi-Supervised Learning on Manifolds
Avleen S. Bijral, Manuel Lladser, and Greg Grudic. Semi-supervised learning of a markovian metric, SIAM Conference on Data Mining, 2008 (To Appear).
Avleen S. Bijral, Markus Breitenbach, and Greg Grudic. Mixture of watson distributions: A generative model for hyperspherical embeddings, AI and Statistics, 2007. (pdf)
Markus Breitenbach and Greg Grudic, Clustering Through Ranking On Manifolds, ICML 2005 (pdf)
Adam Vinueza and Greg Grudic, Unsupervised Outlier Detection and Semi-Supervised Learning, Technical Report CU-CS-976-04, 2004, (pdf)
Probabilistic Regression and Classification
Greg Grudic, Predicting the Probability of Correct Classification, Submitted, Available as Technical Report CU-CS-974-04, 2004, (pdf)
Greg Grudic, Probabilistic Regression Using Basis Function Models, Submitted, Available as Technical Report CU-CS-975-04, 2004, (pdf)
Markus Breitenbach, Rodney Nielsen and Greg Grudic, Probabilistic Random Forests: Predicting Data Point Specific Misclassification Probabilities, Technical Report CU-CS-954-03, 2003, (pdf)
Mimimax Probability Machine Classification and Regression
Markus Breitenbach, Sander M. Bohte and Greg Grudic, Linear Time Nonparametric Classification and Feature Selection with Polynomial MPMC Cascades for large datasets, Available as Technical Report CU-CS-977-04, (pdf)
Sander M. Bohte, Markus Breitenbach and Greg Grudic, Nonparametric Classification with Polynomial MPMC Cascades, ICML 2004, July 4-8 2004, Banff, Canada, (pdf)
T. R. Strohmann, Andrei Belitski, Greg Grudic and Dennis DeCoste. Sparse Greedy Minimax Probability Machine Classification, NIPS 2003 (pdf) [Matlab code]
T. R. Strohmann and G.Z. Grudic. Robust Minimax Probability Machine Regression, Available as Technical Report CU-CS-952-03, 2003 (pdf) [Matlab code]
T. Strohmann and Greg Grudic. A Formulation for Minimax Probability Machine Regression, Neural Information Processing Systems: Natural and Synthetic, NIPS*2003, (pdf) . [Matlab / C code]
Robotics and Reinforcement Learning
Greg Grudic, Vijay Kumar and L. H. Ungar. Using Policy Gradient Reinforcement Learning on Autonomous Robot Controllers, IEEE-RSJ International Conference on Intelligent Robots and Systems (IROS03), 2003 (pdf)
Rate of Convergence in Policy Gradient Reinfocement Learning
Greg Grudic and L. H. Ungar. Rates of Convergence of Performance Gradient Estimates Using Function Approximation and Bias in Reinforcement Learning, Neural Information Processing Systems: Natural and Synthetic, NIPS 2002, (pdf)
Secondary Reinforcers in Reinfocement Learning
Greg Grudic and L. H. Ungar. Exploiting Multiple Secondary Reinforcers in Policy Gradient Reinforcement Learning, Seventeenth International Joint Conference on Artificial Intelligence (IJCAI 01), 2001, (pdf)
Boundary Localized Reinforcement Learning (BLRL):
Greg Grudic and L. H. Ungar. Localizing Search in Reinforcement Learning, Seventeenth National Conference on Artificial Intelligence (AAAI 2000), June 29 - July 2, 2000. (pdf)
The Action Transition Policy Gradient Algorithm (ATPG) for Reinforcement Learning:
Greg Grudic and L. H. Ungar. Localizing Policy Gradient Estimates to Action Transitions, Seventeenth International Conference on Machine Learning (ICML 2000), July 30 - Aug. 3, 2000. (pdf)
Multiple Autonomous Robots:
R. Alur, A. Das, J. Esposito, R. Fierro, Y. Hur, G. Grudic, V. Kumar,I. Lee, J. Ostrowski, G. Pappas, J. Southall, J. Spletzer, and C. Taylor, A framework and Architecture for Multirobot Coordination, Experimental Robotics: LNCS Series, Springer-Verlag, 2001.
R. Fierro, A. Das, J. Spletzer, J. Esposito, V. Kumar, J. P. Ostrowski, G. Pappas, C. J. Taylor, Y. Hur, R. Alur, I. Lee, G. Grudic, and J. Southall, "A framework and architecture for multi-robot coordination," International Journal of Robotics Research (IJRR), vol. 21, no. 10-11, pp. 977-995, Oct-Nov 2002.
Very High Dimensional Nonparametric Regression:
Greg Grudic and P. D. Lawrence. A Nonparametric Learning Approach to Vision Based Mobile Robot Localization. IEEE-RSJ International Conference on Intelligent Robots and Systems (IROS98) , Victoria, B.C., October 1998. (pdf).
Greg Grudic and P. D. Lawrence. Is Nonparametric Learning Practical in Very High Dimensional Spaces?. Fifteenth International Joint Conference on Artificial Intelligence (IJCAI-97) , NAGOYA, Aichi, Japan, August 1997 (pdf)
Human-to-Robot Skill Transfer:
Greg Grudic and P. D. Lawrence. Human-to-Robot Skill Transfer Using the SPORE Approximation. IEEE Int. Conf. on Rob. and Aut. (ICRA'96) , Minneapolis, Minnesota, April 1996. (pdf).
Greg Grudic and P. D. Lawrence. Human-to-Robot Skill Transfer Via Teleoperation. IEEE Int. Conf. on Sys. Man and Cyb. , Vancouver, B.C., October 1995. (pdf).
Robot Manipulator Inverse Kinematics:
Greg Grudic and P. D. Lawrence. Iterative Inverse Kinematics with Manipulator Configuration Control IEEE Trans. Robotics and Automation ,volume 9, Number 4, pages 476-483, August, 1993.
Patents:
Greg Grudic and P. D. Lawrence. System for Determining Manipulator Coordinates US Patent No. 5,293,461.
Greg Grudic, M. F. Kelly and P. D. Lawrence. Mirror Scanner US Patent No. 4,941,739.