Faculty profile 2
Niekum's research focuses on enabling personal robots to be deployed in the home and workplace with minimal intervention by robotics experts. To address this task, his group develops algorithms that allow robots to quickly and robustly characterize new tasks and environments so that well-understood planning and control techniques can be applied automatically. This work draws roughly equally from both machine learning and robotics, including topics such as learning from demonstration, manipulation, time-series analysis, control theory, and reinforcement learning.
P.S. Thomas, S. Niekum, G. Theocharous, and G.D. Konidaris. Policy Evaluation Using the Omega-Return. Advances in Neural Information Processing Systems 29, December 2015.
S. Niekum, S. Osentoski, C.G. Atkeson, and A.G. Barto. Online Bayesian Changepoint Detection for Articulated Motion Models. IEEE International Conference on Robotics and Automation, May 2015.
K. Hausman, S. Niekum, S. Osentoski, and G. Sukhatme. Active Articulation Model Estimation through Interactive Perception. IEEE International Conference on Robotics and Automation, May 2015.
S. Niekum, S. Osentoski, G.D. Konidaris, S. Chitta, B. Marthi, and A.G. Barto. Learning Grounded Finite-State Representations from Unstructured Demonstrations. International Journal of Robotics Research, Vol. 34(2), pages 131-157, February 2015.
S. Niekum, S. Osentoski, S. Chitta, B. Marthi, and Andrew G. Barto. Incremental Semantically Grounded Learning from Demonstration. Robotics: Science and Systems 9, June 2013.
"Discovering Structure in Robotics Tasks via Demonstrations and Active Learning," Invited talk at the AI for Human-Robot Interaction Symposium, AAAI Fall Symposium Series, Arlington, VA, November 2015.
"High-Level Robot Learning from Demonstration," AAAI 2015 Tutorial on Robot Learning from Demonstration, Austin, TX, January 2015.
Senior Program Committee for the International Joint Conference on Artificial Intelligence (IJCAI) 2016.
Program committee for many conferences since 2010 including Neural Information Processing Systems (NIPS), Robotics: Science and Systems (RSS), and the IEEE International Conference on Robotics and Automation (ICRA).
Co-Organizer of the AAAI 2015 Tutorial on Robot Learning from Demonstration, January 2015.
Co-organizer of the RSS 2013 Workshop on Human-Robot Collaboration, June 2013.