About me

I am a Research Scientist at Amazon Robotics. 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.

Previously, I was a Postdoctoral Research Fellow at Mitsubishi Electric Research Laboratories and a Research Affiliate at MIT in Jonathan How’s Aerospace Controls Laboratory. 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

Jun 2025 Our paper on robust dynamics generalization in deep RL is available on arXiv.
May 2025 Our paper on visually robust imitation learning from videos appeared at ICRA 2025.
Apr 2025 I started as a Research Scientist at Amazon Robotics.
Jan 2025 Our paper on physics-informed evidential traversability learning was published in IEEE RA-L.

Selected Publications

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

GRAM: Generalization in deep RL with a robust adaptation module

James Queeney, Xiaoyi Cai, Alexander Schperberg, Radu Corcodel, Mouhacine Benosman, Jonathan P. How

arXiv preprint, 2025

Paper     Code     URL     Video    

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    

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