Graphics enhanced version of this site

Jeremy Martin Kubica
PhD Student

No longer a member of RI.

For more information, see my personal homepage.

Jump to: Research interests | Keywords | Labs & Groups | Projects | Publications

My main research interests are in artificial intelligence, machine learning, and robotics. Specifically, I am interested in the "real world" problems where the information presented is usually very noisy and incomplete. For example, a robot might be programmed to react to a limited set of data from its sensors. This data can be noisy (through normal sensor error), incomplete (through total sensor failures), or even terribly wrong (through undetected sensor failures). How can computers form a meaningful picture from this type of information? Further, how can they make decisions when situated in a dynamic world with this type of noisy information?

artificial intelligence, machine learning, and statistics

• Auton Lab - We build practical large-scale deployments of very highly autonomous self-improving systems.

• Auton Project - Research into Autonomous Learning Software Systems

• Efficient Discovery of Spatial Associations and Structure with Application to Asteroid Tracking
  J.M. Kubica
  doctoral dissertation, tech. report CMU-RI-TR-06-01, Robotics Institute, Carnegie Mellon University, December, 2005. [Abstract]
  Download: pdf [6730 KB] copyrighted

• Scalable and robust group discovery on large transactional data
  P. Choi, A. Moore, and J.M. Kubica
  tech. report CMU-RI-TR-05-60, Robotics Institute, Carnegie Mellon University, December, 2005. [Abstract]
  Download: pdf [753 KB] copyrighted

• Variable KD-Tree Algorithms for Spatial Pattern Search and Discovery
  J.M. Kubica, J. Masiero, A. Moore, R. Jedicke, and A.J. Connolly
  Neural Information Processing Systems, December, 2005. [Abstract]
  Download: pdf [204 KB] copyrighted

• Variable KD-Tree Algorithms for Efficient Spatial Pattern Search
  J.M. Kubica, J. Masiero, A. Moore, R. Jedicke, and A.J. Connolly
  tech. report CMU-RI-TR-05-43, Robotics Institute, Carnegie Mellon University, September, 2005. [Abstract]
  Download: pdf [4417 KB], ps.gz [457 KB] copyrighted

• A Multiple Tree Algorithm for the Efficient Association of Asteroid Observations
  J.M. Kubica, A. Moore, A.J. Connolly, and R. Jedicke
  The Eleventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM Press, August, 2005, pp. 138-146. [Abstract]

• Efficiently Identifying Close Track/Observation Pairs in Continuous Timed Data
  J.M. Kubica, A. Moore, A.J. Connolly, and R. Jedicke
  Proc. SPIE Signal and Data Processing of Small Targets, SPIE, August, 2005. [Abstract]

• Efficient Algorithms for the Identification of Potential Track/Observation Associations in Continuous Time Data
  J.M. Kubica, A. Moore, A.J. Connolly, and R. Jedicke
  tech. report CMU-RI-TR-05-10, Robotics Institute, Carnegie Mellon University, February, 2005. [Abstract]
  Download: pdf [168 KB], ps.gz [375 KB] copyrighted

• Fast and Robust Track Initiation Using Multiple Trees
  J.M. Kubica, A. Moore, A.J. Connolly, and R. Jedicke
  tech. report CMU-RI-TR-04-62, Robotics Institute, Carnegie Mellon University, November, 2004. [Abstract]
  Download: pdf [1196 KB], ps.gz [803 KB] copyrighted

• Spatial Data Structures for Efficient Trajectory-Based Queries
  J.M. Kubica, A. Moore, A.J. Connolly, and R. Jedicke
  tech. report CMU-RI-TR-04-61, Robotics Institute, Carnegie Mellon University, November, 2004. [Abstract]
  Download: pdf [510 KB], ps.gz [278 KB] copyrighted

• Probabilistic Noise Identification and Data Cleaning
  J.M. Kubica and A. Moore
  The Third IEEE International Conference on Data Mining, IEEE Computer Society, November, 2003, pp. 131-138. [Abstract]
  Download: pdf [69 KB], ps.gz [56 KB] copyrighted