RI | People | Boris Sofman

Text only version of this site

Boris Sofman PhD Student Email address: bsofman@andrew.cmu.edu Office: EDSH 232 Phone: (412) 268-3402 Fax: 412-268-5571 Mailing address: Carnegie Mellon University Robotics Institute 5000 Forbes Avenue Pittsburgh, PA 15213 For more information, see my personal homepage.

Jump to: Research interests | Keywords | Projects | Publications

Research interests

I am interested in the study of truly autonomous robotic systems operating in complex, unstructured environments. These systems need to interpret the environment, make efficient plans, and react to uncertainties and their own mistakes. The complexity of many environments, however, makes predetermined behaviors insufficient in many situations. I am researching how on-line learning techniques can enable robots to adjust to such situations by improving their performance with experience. This opens up all sorts of interesting opportunities in pushing the versatility of such systems.

Research interest keywords

3-D perception, artificial intelligence, field robotics, machine learning, mobile robots, motion planning, multi-agent systems, obstacle avoidance, and planning

Current Projects

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.

Publications

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• Improving Robot Navigation Through Self-Supervised Online Learning
  B. Sofman, E.L. Ratliff, J. Bagnell, J. Cole, N. Vandapel, and A. Stentz
  Journal of Field Robotics, Vol. 23, No. 12, December, 2006. [Abstract]
  Download: pdf [2114 KB] copyrighted

• Experimental Analysis of Overhead Data Processing To Support Long Range Navigation
  D. Silver, B. Sofman, N. Vandapel, J. Bagnell, and A. Stentz
  IEEE International Conference on Intelligent Robots and Systems (IROS), October, 2006, pp. 2443 - 2450. [Abstract]
  Download: pdf [1196 KB] copyrighted

• Improving Robot Navigation Through Self-Supervised Online Learning
  B. Sofman, E.L. Ratliff, J. Bagnell, N. Vandapel, and A. Stentz
  Proceedings of Robotics: Science and Systems, August, 2006. [Abstract]
  Download: pdf [1683 KB] copyrighted

• Terrain Classification from Aerial Data to Support Ground Vehicle Navigation
  B. Sofman, J. Bagnell, A. Stentz, and N. Vandapel
  tech. report CMU-RI-TR-05-39, Robotics Institute, Carnegie Mellon University, January, 2006. [Abstract]
  Download: pdf [697 KB] copyrighted