About me

I am a Postdoctoral Research Fellow at Mitsubishi Electric Research Laboratories, and a Research Affiliate at MIT in the Aerospace Controls Laboratory.

I am interested in developing reliable, data-driven algorithms for decision making and control. In order to trust that data-driven methods will deliver reliable performance in complex real-world applications, my research focuses on the need for robustness, safety, and generalization. I primarily explore these topics in the context of deep reinforcement learning, imitation learning, and self-supervised learning, with applications in robotics.

I received my PhD in systems engineering from Boston University, where I was advised by Yannis Paschalidis and Christos Cassandras. I also hold a MS in systems engineering from Boston University, and a BA in mathematics and mathematical economics from Colgate University.

Selected News

Jan 2025 Our paper on physics-informed evidential traversability learning was published in IEEE RA-L.
Jan 2025 Our paper on visually robust imitation learning from videos was accepted to ICRA 2025.
Dec 2024 New paper on robust dynamics generalization in deep RL is now available on arXiv.
Mar 2024 Our paper on optimal transport perturbations for robust and safe RL was published in TMLR.
Dec 2023 Our paper on risk-averse model uncertainty for safe RL appeared at NeurIPS 2023.
Aug 2023 I started as a Postdoctoral Research Fellow at Mitsubishi Electric Research Laboratories, and a Research Affiliate at MIT in the Aerospace Controls Laboratory.
Aug 2023 I received my PhD in systems engineering from Boston University after successfully defending my dissertation on reliable deep reinforcement learning.

Selected Publications

Check out the Publications page for a full list of my publications.

PIETRA: Physics-informed evidential learning for traversing out-of-distribution terrain

Xiaoyi Cai, James Queeney, Tong Xu, Aniket Datar, Chenhui Pan, Max Miller, Ashton Flather, Philip R. Osteen, Nicholas Roy, Xuesu Xiao, Jonathan P. How

IEEE Robotics and Automation Letters, 2025 (RA-L)

Paper     URL     Video    

GRAM: Generalization in deep RL with a robust adaptation module

James Queeney, Xiaoyi Cai, Mouhacine Benosman, Jonathan P. How

arXiv preprint, 2024

Paper     Code     URL    

Optimal transport perturbations for safe reinforcement learning with robustness guarantees

James Queeney, Erhan Can Ozcan, Ioannis Ch. Paschalidis, Christos G. Cassandras

Transactions on Machine Learning Research, 2024 (TMLR)

Paper     Code     URL    

Risk-averse model uncertainty for distributionally robust safe reinforcement learning

James Queeney, Mouhacine Benosman

Advances in Neural Information Processing Systems, 2023 (NeurIPS 2023)

Paper     Code     URL