94 citations · 391 across the 65 of their papers we have counts for
7 papers · 1 filter
Learning Hybrid Control Barrier Functions from Data
Lars Lindemann, Haimin Hu, Alexander Robey +4
Motivated by the lack of systematic tools to obtain safe control laws for hybrid systems, we propose an optimization-based framework for learning certifiably safe control laws from…
Data-Driven System Level Synthesis
Anton Xue, Nikolai Matni
We establish data-driven versions of the System Level Synthesis (SLS) parameterization of achievable closed-loop system responses for a linear-time-invariant system over a finite-h…
Learning Stability Certificates from Data
Nicholas M. Boffi, Stephen Tu, Nikolai Matni +2
Many existing tools in nonlinear control theory for establishing stability or safety of a dynamical system can be distilled to the construction of a certificate function that guara…
Robust, Perception Based Control with Quadrotors
Laura Jarin-Lipschitz, Rebecca Li, Ty Nguyen +2
Traditionally, controllers and state estimators in robotic systems are designed independently. Controllers are often designed assuming perfect state estimation. However, state esti…
Learning Control Barrier Functions from Expert Demonstrations
Alexander Robey, Haimin Hu, Lars Lindemann +4
Inspired by the success of imitation and inverse reinforcement learning in replicating expert behavior through optimal control, we propose a learning based approach to safe control…
An Adversarial Objective for Scalable Exploration
Bernadette Bucher, Karl Schmeckpeper, Nikolai Matni +1
Model-based curiosity combines active learning approaches to optimal sampling with the information gain based incentives for exploration presented in the curiosity literature. Exis…
PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
Sangdon Park, Osbert Bastani, Nikolai Matni +1
We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i…