Nikolai Matni
Associate Professor, ESE
Nikolai Matni is an Associate Professor in the Department of Electrical and Systems Engineering. Prior to joining Penn, Nikolai was a postdoctoral scholar in EECS at UC Berkeley. He has also held a position as a postdoctoral scholar in the Computing and Mathematical Sciences at Caltech. He received his Ph.D. in Control and Dynamical Systems from Caltech in June 2016. He also holds B.A.Sc. and M.A.Sc. in Electrical Engineering from the University of British Columbia, Vancouver, Canada. His research interests broadly encompass the use of learning, optimization, and control in the design and analysis of safety-critical and data-driven cyber-physical systems.
Research Areas
- Perception-based Control
- Distributed and Decentralized Control
- Hybrid Control Systems
- Learning for Control Systems
- Nonlinear Control Systems
- Perception-based Control
- Robust and Optimized Control
- Autonomy
- Machine Learning
Publications
Publisher ICRA
Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomy
Publisher AIAA
Occupancy-aware Trajectory Planning for Autonomous Valet Parking in Uncertain Dynamic Environments
Publisher arXiv
Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error
Publisher CDC
Policy Gradient for LQR with Domain Randomization
Publisher CDC
Verification of Sequential Convex Programming for Parametric Non-convex Optimization
Publisher ArXiv
Publisher ArXiv
Nearly Instance-Optimal Parameter Recovery from Many Trajectories via Hellinger Localization
Publisher ArXiv
Learning Acceleration Algorithms for Fast Parametric Convex Optimization with Certified Robustness
Publisher ArXiv
Publisher ArXiv
Graph-based Path Planning with Dynamic Obstacle Avoidance for Autonomous Parking
Publisher IEEE Intelligent Vehicles Symposium
Quad-LCD: Layered Control Decomposition Enables Actuator-Feasible Quadrotor Trajectory Planning
Publisher ArXiv
Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control
Publisher AAAI Conference on Artificial Intelligence
On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
Publisher ArXiv
Logarithmic Regret for Nonlinear Control
Publisher ArXiv
Closed-Loop Analysis of ADMM-Based Suboptimal Linear Model Predictive Control
Publisher IEEE Control Systems Letters
Coordinating Planning and Tracking in Layered Control Policies via Actor-Critic Learning
Publisher CDC
Moving average estimation by geometric optimization
Publisher CDC
Single trajectory conformal prediction
Publisher CDC
Performance–Robustness Tradeoffs in Adversarially Robust Control and Estimation
Publisher IEEE Transactions on Automatic Control
Publisher ICML
Uncertainty-Aware Deployment of Pre-trained Language-Conditioned Imitation Learning Policies
Publisher IROS
The GRASP Lab [Institutes in Control]
Publisher IEEE Control Systems
Nonasymptotic regret analysis of adaptive linear quadratic control with model misspecification
Publisher Learning for Dynamics & Control Conference
A Quantitative Framework for Layered Multirate Control: Toward a Theory of Control Architecture
Publisher IEEE Control Systems
Learning Robust Output Control Barrier Functions From Safe Expert Demonstrations
Publisher IEEE Open Journal of Control Systems
Robust Model Predictive Control with Polytopic Model Uncertainty through System Level Synthesis
Publisher Automatica
Uncertainty-driven Planner for Exploration and Navigation
Publisher IEEE Robotics and Automation Society - ICRA
An Adversarial Objective for Scalable Exploration
Publisher IROS
How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?
Publisher L4DC
Publisher arXiv
Evaluating Robust, Perception Based Controllers with Quadrotors
Publisher IEEE International Conference on Intelligent Robots and Systems (IROS)
News
Faculty News
George Pappas and Nikolai Matni Receive 2024 IEEE Control Systems Society Best Paper Awards
December 18, 2024
Faculty News
AFOSR awards $21.5M to scientists, engineers via Young Investigator Program
January 12, 2024
Faculty News
December 12, 2023
Ph.D. Students
Research Staff
Alumni
PhD, ESE '26 - Scientist I, Robotics, Dexterous Manipulation & Robot Learning, Lila Sciences
Robotics MSE '19, PhD ESE '23, PostDoc CIS '23 - Robotics Software Engineer, Asylon Robotics
Research Areas
- Perception-based Control
- Distributed and Decentralized Control
- Hybrid Control Systems
- Learning for Control Systems
- Nonlinear Control Systems
- Perception-based Control
- Robust and Optimized Control
- Autonomy
- Machine Learning