Lab Affiliation(s):
Interactive Robotics Group (IRG)
Advisor:
Julie Shah
Areas of Expertise:
  • Artificial Intelligence
  • Human-Robot Interaction
  • Optimization
Expected date of graduation:
February 27, 2017

Matthew Gombolay

  • PhD

Department: 

  • Aeronautics and Astronautics

Lab Affiliation(s): 

Interactive Robotics Group (IRG)

Advisor: 

Julie Shah

Top 3 Areas of Expertise: 

Artificial Intelligence
Human-Robot Interaction
Optimization

Expected date of graduation: 

February 27, 2017

CV: 

Thesis Title: 

Human-Machine Collaborative Optimization via Apprenticeship Scheduling

Thesis Abstract: 

Resource optimization in health care, manufacturing, and military operations requires the careful choreography of people and equipment to effectively fulfill the responsibilities of the profession. However, resource optimization is a computationally challenging problem, and poorly utilizing resources can have drastic consequences. Within these professions, there are human domain experts who are able to learn from experience to develop strategies, heuristics, and rules-of-thumb to effectively utilize the resources at their disposal. Manually codifying these heuristics within a computational tool is a laborious process and leaves much to be desired. Even with a codified set of heuristics, it is not clear how to best insert an autonomous decision-support system into the human decision-making process. In this thesis, I develop an autonomous computational method that first, learns domain-expert strategies from human scheduling demonstration, second, leverages these strategies to efficiently solve computationally intractable optimization problems and, third, provide engaging decision-support for operators in the field. I demonstrate the power of this framework in simulation and on a physical robot platform with real domain experts in military operations and health care.

Top 5 Awards and honors (name of award, date received): 

National Training and Simulation Association Modeling & Simulation Team Training Award, December 2015
AAAI-15 Robotics Fellowship, January 2015
Best Intelligent Systems Paper Award (AIAA), August 2013
Human-Robot Interaction Pioneer, March 2013
NSF Graduate Research Fellowship Program, September 2011

5 Recent Papers: 

Gombolay, M. C., Stigile, J., Jensen, R., Son, S.-H., and Shah, J. A. (2016). Apprenticeship Scheduling: Learning to Schedule from Human Experts. In Proc. International Joint Conference on Artificial Intelligence (IJCAI). [25% Acceptance Rate] URL: http://people.csail.mit.edu/gombolay/Publications/Gombolay_IJCAI_2016.pdf.

Gombolay, M. C., Yang, X. J., Hayes, B., Seo, N., Liu, Z., Wadhwania, Z., Yu, T., Shah, N., Golen, T., and Shah, J. A. (2016). Robotic Assistance in Coordination of Patient Care. In Proc. Robotics: Science and Systems (RSS). [24% Acceptance Rate] URL: http://people.csail.mit.edu/gombolay/Publications/Gombolay_RSS_2016.pdf.

Gombolay, M. C., Gutierrez, R., Sturla, G., Shah., J. A. (2015), Decision-Making Authority, Team Efficiency, and Human Worker Satisfaction in Mixed Human-Robot Teams. Autonomous Robots, 39(3), 293-312.12. URL: http://people.csail.mit.edu/gombolay/Publications/Gombolay_AuRo_2015.pdf.

Gombolay, M. C. and Shah, J. A. (2014). Schedulability Analysis of Task Sets with Upper and Lowerbound Temporal Constraints. Journal of Aerospace Information Systems, 11(12), 821-841. URL: http://people.csail.mit.edu/gombolay/Publications/Gombolay_JAIS_2014.pdf.

Gombolay, M. C., et al. (2014), Decision-Making Authority, Team Efficiency, and Human Worker Satisfaction in Mixed Human-Robot Teams. In Proc. Robotics: Science and Systems (RSS), 2014. [32% Acceptance Rate] URL: http://people.csail.mit.edu/gombolay/Publications/Gombolay_RSS_2014.pdf.

Gombolay, M. C., Wilcox, R., Shah., J. A. (2013), Fast Scheduling of Multi-Robot Teams with Temporospatial Constraints. In Proc. Robotics: Science and Systems (RSS), 2013. [30% Acceptance Rate] URL: http://people.csail.mit.edu/gombolay/Publications/Gombolay_RSS_2013.pdf

Contact Information: