I am a researcher at the Renault-Nissan-Mitsubishi Alliance Innovation Center - Silicon Valley. I design and implement artificial intelligence techniques for decision-making on robots, such as autonomous vehicles, for long-term autonomy.
I earned my doctorate in computer science at the University of Massachusetts Amherst, advised by Dr. Shlomo Zilberstein, specializing in artificial intelligence applied to autonomous robots. Previously, I earned my bachelor's and master's degrees in computer science, engineering, and mathematics from the University of Massachusetts Amherst and The Pennsylvania State University.
Please see my CV for more details.
My research interests are broadly automated planning, autonomous robotics, and reinforcement learning, in both single- and multi-agent scenarios, for long-term autonomy. In particular, I am interested in the mathematically principled design of multiple specialized MDPs, POMDPs, and Dec-POMDPs to solve complex real-world problems, which are integrated together in a robotic system via hierarchical and multi-objective relationships.
May 2019: I have officially graduated with my doctorate in computer science!
March 2019: I have successfully defended my dissertation: Abstractions in Reasoning for Long-Term Autonomy!
January 2019: Our paper on generalized controllers for POMDPs was accepted to ICRA 2019! It generalizes popular approximate POMDP policy forms used in point-based, FSC, and compression algorithms under one unified controller family form.
January 2019: Our AAMAS 2019 paper on policy networks was accepted as an extended abstract. It generalizes many popular models of hierarchies and multiple objectives, such as CMDPs and the options framework, as well as unifying much of my research. For an extensive presentation of policy networks, please read my dissertation later this year!
October 2018: Our AAAI fall symposium on long-term autonomy that I chaired was held in Arlington, VA! Thank you to all those who participated and made the symposium a success!
June 2018: I have been awarded Nissan's Patent Research Award for my work at the Nissan Research Center!
April 2018: Our IJCAI 2018 paper on meta-reasoning for determining the optimal stopping point in anytime algorithms. It has another video of the 'epic' library for path planning from our IROS 2016 paper!
January 2018: I am the primary inventor on another six international patent applications for autonomous vehicles!
November 2017: Our paper on integrating cooperation and competition (Dec-POMDP and POSG) was accepted to AAAI 2018! It has a multi-robot video using a hybrid Dec-POMDP and POSG with stochastic FSC policies!
July 2017: A paper on a very simple belief point compression technique called a σ-approximation was accepted to IROS 2017. It has an accompanying video of a robot using a POMDP!
April 2017: Our conference paper on MODIA, which is a method for online scalable decision-making with applications to autonomous vehicles, was accepted to IJCAI 2017!
February 2017: I am the primary inventor on four international patent applications for autonomous vehicles!
November 2016: Our AAAI 2017 paper on a short-sighted labeling algorithm for quickly solving SSPs entitled FLARES was accepted.
July 2016: Our IROS 2016 paper on robot path planning using harmonic functions and GPUs was accepted. This includes the 'epic' library for path planning in ROS.
January 2016: Our AAMAS 2016 paper was accepted as an extended abstract.
December 2015: I have passed my qualifying exam with distinction! Now I am a Ph.D. candidate!
November 2015: Our AAAI 2016 paper on proactive learning POMDPs has been accepted.
August 2015: Both a GPU-based POMDP algorithm paper and a relaxed LMDP paper have been accepted to the SDMIA as part of the AAAI Fall Symposium 2015 Series. The POMDP short paper presents our 'nova' library for planning.
April 2015: Our IJCAI 2015 paper on Lexicographic POMDPs has been accepted.
November 2014: Our AAAI 2015 paper on Lexicographic MDPs has been accepted.
March 2014: I have received the Outstanding Teaching Assistant Award!