Graphics enhanced version of this site

James (Drew) Bagnell
Research Scientist

Associated center: NREC

Email address: bagnell2@andrew.cmu.edu
Office: NSH 3111
Phone: (412) 681-8669

Mailing address:
National Robotics Engineering Center
10 40th Street
Pittsburgh, PA 15201

For more information, see my personal homepage.

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

I am interested in "closing the loop" on complex systems; that is, I am interested in designing algorithms that allow systems to observe their own operation and improve performance. My belief is that the border land between planning, control and computational learning is particularly rich with research challenges and potential to make real, immediate impact on applications. I'm particularly interested in systems for which we can obtain at best a partial model. To this end, I'm excited about extending research tools that come from information theory, statistics, control theory, statistical physics and optimization.

At the moment, I am particularly focused on two areas in machine learning. First I am working on applications of learning and decision making applied to mobile robotics. Second, I am interested in developing rich, structured probabilistic models that are appropriate for both making and learning decisions.

artificial intelligence, control, machine learning, mobile robots, and planning

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

• Learning Locomotion - Robust planning and control of the quadruped robot "Little Dog" to traverse rough terrain (DARPA sponsored).
• Quality of Life Technology Center - QoLT is a unique partnership between Carnegie Mellon and the University of Pittsburgh that brings together a cross-disciplinary team of technologists, clinicians, industry partners, end users, and other stakeholders to create revolutionary technologies that will improve and sustain the quality of life for all people.
• Tartan Racing - Carnegie Mellon University is teaming with General Motors to compete in the 2007 DARPA Urban Challenge.
• UGCV PerceptOR Integrated - The UPI (UGCV PerceptOR Integrated) program integrates and enhances the results from UGCV and PerceptOR to increase the speed and autonomy of unmanned ground vehicles operating in complex terrain. By combining the inherent mobility of Spinner with advanced perception techniques including the use of learning and prior terrain data, the UPI program stresses system design across vehicle, sensors and software so that the strengths of one component compensate for the weaknesses of another.
• Urban Challenge

• Maximum Entropy Inverse Reinforcement Learning
  B.D. Ziebart, A. Maas, J. Bagnell, and A.K. Dey
  Proceeding of AAAI 2008, July, 2008. [Abstract]
  Download: pdf [293 KB] copyrighted

• Adaptive Workspace Biasing for Sampling Based Planners
  M. Zucker, J. Kuffner, and J. Bagnell
  Proc. IEEE Int'l Conf. on Robotics and Automation, May, 2008. [Abstract]
  Download: pdf [976 KB] copyrighted

• Imitation Learning for Locomotion and Manipulation
  N. Ratliff, J. Bagnell, and S. Srinivasa
  tech. report CMU-RI-TR-07-45, Robotics Institute, Carnegie Mellon University, December, 2007. [Abstract]
  Download: pdf [2236 KB] copyrighted

• Imitation Learning for Locomotion and Manipulation
  N. Ratliff, J. Bagnell, and S. Srinivasa
  IEEE-RAS International Conference on Humanoid Robots, November, 2007. [Abstract]

• Learning Selectively Conditioned Forest Structures with Applications to DBNs and Classification
  B.D. Ziebart, A.K. Dey, and J. Bagnell
  Proceedings of Uncertainty in Artificial Intelligence (UAI 2007), July, 2007. [Abstract]
  Download: pdf [339 KB] copyrighted

• Vegetation Detection for Driving in Complex Environments
  D. Bradley, R. Unnikrishnan, and J. Bagnell
  IEEE International Conference on Robotics and Automation, April, 2007. [Abstract]
  Download: pdf [1694 KB] copyrighted

• (Online) Subgradient Methods for Structured Prediction
  N. Ratliff, J. Bagnell, and M. Zinkevich
  Eleventh International Conference on Artificial Intelligence and Statistics (AIStats), March, 2007. [Abstract]
  Download: pdf [375 KB] copyrighted

• Creating Low-Cost Soil Maps for Tropical Agriculture using Gaussian Processes
  J.P. Gonzalez, S. Cook, T. Oberthur, A. Jarvis, J. Bagnell, and M.B. Dias
  Workshop on AI in ICT for Development (ICTD) at the Twentieth International Joint Conference on Artificial Intelligence (IJCAI 2007), January, 2007. [Abstract]
  Download: pdf [856 KB] copyrighted

• Kernel Conjugate Gradient for Fast Kernel Machines
  N. Ratliff and J. Bagnell
  International Joint Conference on Artificial Intelligence, Vol. 20, January, 2007. [Abstract]
  Download: pdf [6617 KB] copyrighted

• Boosting Structured Prediction for Imitation Learning
  N. Ratliff, D. Bradley, J. Bagnell, and J. Chestnutt
  Advances in Neural Information Processing Systems 19, MIT Press, Cambridge, MA, 2007. [Abstract]
  Download: pdf [847 KB] copyrighted