Chelsea Sidrane

Research Interests

My current primary research focus is on verification for machine learning-enabled autonomous robotic systems. I am particularly interested in analyzing systems where machine learning is part of the feedback control loop and the inputs lie in state space, rather than pixel space.

In my current position at KTH, I am applying my skills -- a combination of dynamical systems and control theory, machine learning, and formal methods -- to  problems of control and planning for underwater robotic vehicles with an eye towards environmental monitoring and conservation. 

My PhD thesis focused on methods for assuring the safety and reliability of machine learning systems. This is especially important when machine learning is used in safety-critical applications like cars, planes, and spacecraft. In particular, I spent four years developing methods to verify neural networks used within nonlinear systems. 

Broadly, I am interested in applying formal methods to learning enabled systems so that we can develop more reliable data-driven algorithms. When possible, I am motivated by application domains that have socially-relevant, climate-relevant or human-focused impact.  

If you are interested in these areas as well and would like to connect please reach out to me at chelse@kth.se.

Publications 🎓

Under Review

• Chelsea Sidrane, Sydney Katz, Anthony Corso, Mykel Kochenderfer. Verifying Inverse Model Neural Networks. https://arxiv.org/abs/2202.02429

Peer-Reviewed Journal Papers

• Nicholas Rober, Sydney Katz, Chelsea Sidrane, Esen Yel, Michael Everett, Mykel J. Kochenderfer, Jonathon P. How. Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems. 2023.

• Chelsea Sidrane*, Amir Maleki*, Ahmed Irfan, Mykel Kochenderfer. OVERT: An Algorithm for Safety Verification of Neural Network Control Policies for Nonlinear Systems. Journal of Machine Learning Research (JMLR), 2022. http://jmlr.org/papers/v23/21-0847.html (* denotes equal contribution)

Peer-Reviewed Conference Papers

• Sidrane, Chelsea, and Jana Tumova. "BURNS: Backward Underapproximate Reachability for Neural-Feedback-Loop Systems." Accepted to Learning for Dynamics & Control (L4DC) 2026.

• Verhagen, Joris, Elias Krantz, Chelsea Sidrane, David Dörner, Nicola De Carli, Pedro Roque, Huina Mao, Gunnar Tibert, Ivan Stenius, Christer Fuglesang, Dimos Dimarogonas, Jana Tumova. “Validation of Space Robotics in Underwater Environments via Disturbance Robustness Equivalency.” ICRA 2026.

• Akinwande, Samuel, Chelsea Sidrane, Mykel J. Kochenderfer, Clark Barrett. "Verifying Nonlinear Neural Feedback Systems using Polyhedral Enclosures." Learning for Dynamics & Control (L4DC) 2026.

• Schmidt, Jule, Xin Tao, Chelsea Sidrane, Swarup Kumar Mohalik, Ahkil Prasad, Jana  Tumova, and Nils Jansen. “A Case for Causal Reinforcement Learning in Longitudinal Vehicle Control”. ICAART 2026.

• Chelsea Sidrane and Jana Tumova. TTT: A Temporal Refinement Heuristic for Tenuously Tractable Discrete Time Reachability Problems. ACC 2025. https://arxiv.org/pdf/2407.14394 

• Kiessling, Alexander, Ignacio Torroba, Chelsea Rose Sidrane, Ivan Stenius, Jana Tumova, and John Folkesson. Efficient Non-Myopic Layered Bayesian Optimization For Large-Scale Bathymetric Informative Path Planning. ICRA, 2025. 

• Michael Kelly, Chelsea Sidrane, Katherine Driggs-Campbell and Mykel J. Kochenderfer. HG-DAgger: Interactive Imitation Learning with Human Experts. International Conference on Robotics and Automation (ICRA), 2019. https://arxiv.org/abs/1810.02890 

• Chelsea Sidrane, Mykel J. Kochenderfer.​ C​losed-Loop Planning for Disaster Evacuation with Stochastic Arrivals.​ ​IEEE International Conference on Intelligent Transportation Systems (ITSC), 2018. https://drive.google.com/open?id=1l4Quv2XuYloIRcbrATVhYax8eJVku2ip 

Peer-Reviewed Workshop Papers

• Chelsea Sidrane. Safety assurance for systems with machine learning components. Doctoral Consortium, AAAI Conference on Artificial Intelligence (AAAI), 2021. 

• Taylor T. Johnson, Diego Manzanas Lopez, Patrick Musau, Hoang-Dung Tran, Elena Botoeva, Francesco Leofante, Amir Maleki, Chelsea Sidrane, Jiameng Fan, Chao Huang. ARCH-COMP20 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants. International Workshop on Applied Verification of Continuous and Hybrid Systems, 2020. https://easychair.org/publications/paper/Jvwg

• Chelsea Sidrane, Dylan J. Fitzpatrick, Andrew Annex, Diane O'Donoghue, Yarin Gal, and Piotr Biliński. ​Machine Learning for Generalizable Prediction of Flood Susceptibility​. ​NeurIPS 2019​ ​Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop​. a​rXiv:1910.06521 (2019). 

• Chelsea Sidrane and Mykel J. Kochenderfer. ​OVERT: Verification of Nonlinear Dynamical Systems with Neural Network Controllers via Overapproximation.​ SafeML ICLR 2019. https://drive.google.com/uc?export=download&id=17dj7HXXzjGymoh1VUm4sfb7ynQ_R0Xem 

•  Michael Kelly, Chelsea Sidrane, Katherine Driggs-Campbell and Mykel J. Kochenderfer. ​Safe Interactive Imitation Learning from Humans.​ ​NeurIPS 2018 Imitation Learning and its Challenges in Robotics. https://drive.google.com/open?id=18rJr7eXPa9rEvapyrQOfjgyQtSlMd03y 

Open Source Software

OVERT.jl

Nonlinear Overapproximation     

https://github.com/sisl/OVERT.jl

OVERTVerify.jl

Reachability for Nonlinear Systems with Neural Network Control Policies

https://github.com/sisl/OVERTVerify.jl

Background

I was born and raised in the suburbs of New York City. I received my Bachelor's degree in Mechanical Engineering from Cornell University in 2016 and my Master's and PhD degrees from Stanford University in 2022. My interests include singing, comedy, cooking, skiing, hiking, ultimate frisbee, and memes.