Aerospace Controls Laboratory

LinkedIn  /  Homepage
lutjens [at] mit [dot] edu
31-238A

Education

• S.M. in Aeronatics and Astronautics, Autonomous Systems, MIT, 2019
• B.Sc. in Engineering Science, MIT, 2017

Research Interests

• Robust and Interpretable AI
• Safe Reinforcement Learning
• Bayesian Deep Learning

Awards

• Deutschlandstipendium Scholarship, 2014 - 2017
• JASSO Scholarship, 2016

Projects

Certified Adversarial Robustness for Deep RL
Michael Everett, Björn Lütjens, 2020

This project develops deep RL algorithms that are robust to an adversarial perturbation in the observation space

Robust and Interpretable RL for Navigation in Pedestrian Crowds
Björn Lütjens, Michael Everett, 2018

Deep neural networks can fail overconfidently on novel observations. This work pioneers a reinforcement learning framework that reasons about the predictive confidence and is more robust to novel observations.