Search Results for author: Nikolai Matni

Found 55 papers, 21 papers with code

Convex Relaxations of SE(2) and SE(3) for Visual Pose Estimation

no code implementations15 Jan 2014 Matanya B. Horowitz, Nikolai Matni, Joel W. Burdick

The method is a convex relaxation of the classical pose estimation problem, and is based on explicit linear matrix inequality (LMI) representations for the convex hulls of $SE(2)$ and $SE(3)$.

Pose Estimation

On the Sample Complexity of the Linear Quadratic Regulator

no code implementations4 Oct 2017 Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, Stephen Tu

This paper addresses the optimal control problem known as the Linear Quadratic Regulator in the case when the dynamics are unknown.

Finite-Data Performance Guarantees for the Output-Feedback Control of an Unknown System

1 code implementation25 Mar 2018 Ross Boczar, Nikolai Matni, Benjamin Recht

As the systems we control become more complex, first-principle modeling becomes either impossible or intractable, motivating the use of machine learning techniques for the control of systems with continuous action spaces.

Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator

no code implementations NeurIPS 2018 Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, Stephen Tu

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs.

Safely Learning to Control the Constrained Linear Quadratic Regulator

2 code implementations26 Sep 2018 Sarah Dean, Stephen Tu, Nikolai Matni, Benjamin Recht

We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques.

Learning Sparse Dynamical Systems from a Single Sample Trajectory

no code implementations20 Apr 2019 Salar Fattahi, Nikolai Matni, Somayeh Sojoudi

In particular, we show that the proposed estimator can correctly identify the sparsity pattern of the system matrices with high probability, provided that the length of the sample trajectory exceeds a threshold.

A Tutorial on Concentration Bounds for System Identification

no code implementations27 Jun 2019 Nikolai Matni, Stephen Tu

We provide a brief tutorial on the use of concentration inequalities as they apply to system identification of state-space parameters of linear time invariant systems, with a focus on the fully observed setting.

From self-tuning regulators to reinforcement learning and back again

no code implementations27 Jun 2019 Nikolai Matni, Alexandre Proutiere, Anders Rantzer, Stephen Tu

Machine and reinforcement learning (RL) are increasingly being applied to plan and control the behavior of autonomous systems interacting with the physical world.

reinforcement-learning Reinforcement Learning (RL)

Robust Guarantees for Perception-Based Control

no code implementations L4DC 2020 Sarah Dean, Nikolai Matni, Benjamin Recht, Vickie Ye

Motivated by vision-based control of autonomous vehicles, we consider the problem of controlling a known linear dynamical system for which partial state information, such as vehicle position, is extracted from complex and nonlinear data, such as a camera image.

Autonomous Vehicles Position

Efficient Learning of Distributed Linear-Quadratic Controllers

no code implementations21 Sep 2019 Salar Fattahi, Nikolai Matni, Somayeh Sojoudi

In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems.

Sample Complexity of Kalman Filtering for Unknown Systems

no code implementations L4DC 2020 Anastasios Tsiamis, Nikolai Matni, George J. Pappas

We show that when the system identification step produces sufficiently accurate estimates, or when the underlying true KF is sufficiently robust, that a Certainty Equivalent (CE) KF, i. e., one designed using the estimated parameters directly, enjoys provable sub-optimality guarantees.

PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction

1 code implementation ICLR 2020 Sangdon Park, Osbert Bastani, Nikolai Matni, Insup Lee

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. e., the confidence set for a given input contains the true label with high probability.

Generalization Bounds Learning Theory +3

An Adversarial Objective for Scalable Exploration

1 code implementation13 Mar 2020 Bernadette Bucher, Karl Schmeckpeper, Nikolai Matni, Kostas Daniilidis

Model-based curiosity combines active learning approaches to optimal sampling with the information gain based incentives for exploration presented in the curiosity literature.

Active Learning

Learning Control Barrier Functions from Expert Demonstrations

1 code implementation7 Apr 2020 Alexander Robey, Haimin Hu, Lars Lindemann, Hanwen Zhang, Dimos V. Dimarogonas, Stephen Tu, Nikolai Matni

Furthermore, if the CBF parameterization is convex, then under mild assumptions, so is our learning process.

Learning Stability Certificates from Data

no code implementations13 Aug 2020 Nicholas M. Boffi, Stephen Tu, Nikolai Matni, Jean-Jacques E. Slotine, Vikas Sindhwani

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 guarantees a desired property.

Learning Hybrid Control Barrier Functions from Data

no code implementations8 Nov 2020 Lars Lindemann, Haimin Hu, Alexander Robey, Hanwen Zhang, Dimos V. Dimarogonas, Stephen Tu, Nikolai Matni

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.

Data-Driven System Level Synthesis

1 code implementation20 Nov 2020 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-horizon.

Learning Robust Hybrid Control Barrier Functions for Uncertain Systems

1 code implementation16 Jan 2021 Alexander Robey, Lars Lindemann, Stephen Tu, Nikolai Matni

We identify sufficient conditions on the data such that feasibility of the optimization problem ensures correctness of the learned robust hybrid control barrier functions.

On the Sample Complexity of Stability Constrained Imitation Learning

no code implementations18 Feb 2021 Stephen Tu, Alexander Robey, Tingnan Zhang, Nikolai Matni

We study the following question in the context of imitation learning for continuous control: how are the underlying stability properties of an expert policy reflected in the sample-complexity of an imitation learning task?

Continuous Control Generalization Bounds +1

How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?

1 code implementation2 Apr 2021 Jingxi Xu, Bruce Lee, Nikolai Matni, Dinesh Jayaraman

The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues of controllability/observability gramians.

Reinforcement Learning (RL)

STL Robustness Risk over Discrete-Time Stochastic Processes

no code implementations3 Apr 2021 Lars Lindemann, Nikolai Matni, George J. Pappas

We then define the risk of a stochastic process not satisfying an STL formula robustly, referred to as the STL robustness risk.

Communication Topology Co-Design in Graph Recurrent Neural Network Based Distributed Control

1 code implementation28 Apr 2021 Fengjun Yang, Nikolai Matni

Our proposed parameterization enjoys a local and distributed architecture, similar to previous Graph Neural Network (GNN)-based parameterizations, while further naturally allowing for joint optimization of the distributed controller and communication topology needed to implement it.

System Level Synthesis-based Robust Model Predictive Control through Convex Inner Approximation

1 code implementation10 Nov 2021 Shaoru Chen, Nikolai Matni, Manfred Morari, Victor M. Preciado

We propose a robust model predictive control (MPC) method for discrete-time linear time-invariant systems with norm-bounded additive disturbances and model uncertainty.

Model Predictive Control

Adversarial Tradeoffs in Robust State Estimation

no code implementations17 Nov 2021 Thomas T. C. K. Zhang, Bruce D. Lee, Hamed Hassani, Nikolai Matni

We provide an algorithm to find this perturbation given data realizations, and develop upper and lower bounds on the adversarial state estimation error in terms of the standard (non-adversarial) estimation error and the spectral properties of the resulting observer.

Learning Robust Output Control Barrier Functions from Safe Expert Demonstrations

1 code implementation18 Nov 2021 Lars Lindemann, Alexander Robey, Lejun Jiang, Satyajeet Das, Stephen Tu, Nikolai Matni

Along with the optimization problem, we provide verifiable conditions in terms of the density of the data, smoothness of the system model and state estimator, and the size of the error bounds that guarantee validity of the obtained ROCBF.

Autonomous Driving

Adversarially Robust Stability Certificates can be Sample-Efficient

no code implementations20 Dec 2021 Thomas T. C. K. Zhang, Stephen Tu, Nicholas M. Boffi, Jean-Jacques E. Slotine, Nikolai Matni

Motivated by bridging the simulation to reality gap in the context of safety-critical systems, we consider learning adversarially robust stability certificates for unknown nonlinear dynamical systems.

Data-driven Distributed and Localized Model Predictive Control

2 code implementations22 Dec 2021 Carmen Amo Alonso, Fengjun Yang, Nikolai Matni

By imposing locality constraints on the system response, we show that the amount of data needed for our synthesis problem is independent of the size of the global system.

Model Predictive Control

Linear Variational State-Space Filtering

1 code implementation4 Jan 2022 Daniel Pfrommer, Nikolai Matni

We introduce Variational State-Space Filters (VSSF), a new method for unsupervised learning, identification, and filtering of latent Markov state space models from raw pixels.

Single Trajectory Nonparametric Learning of Nonlinear Dynamics

no code implementations16 Feb 2022 Ingvar Ziemann, Henrik Sandberg, Nikolai Matni

Given a single trajectory of a dynamical system, we analyze the performance of the nonparametric least squares estimator (LSE).

counterfactual

Uncertainty-driven Planner for Exploration and Navigation

1 code implementation24 Feb 2022 Georgios Georgakis, Bernadette Bucher, Anton Arapin, Karl Schmeckpeper, Nikolai Matni, Kostas Daniilidis

We consider the problems of exploration and point-goal navigation in previously unseen environments, where the spatial complexity of indoor scenes and partial observability constitute these tasks challenging.

Robust Model Predictive Control with Polytopic Model Uncertainty through System Level Synthesis

2 code implementations21 Mar 2022 Shaoru Chen, Victor M. Preciado, Manfred Morari, Nikolai Matni

However, it is challenging to design LTV state feedback controllers in the face of model uncertainty whose effects are difficult to bound.

Model Predictive Control

Performance-Robustness Tradeoffs in Adversarially Robust Linear-Quadratic Control

no code implementations21 Mar 2022 Bruce D. Lee, Thomas T. C. K. Zhang, Hamed Hassani, Nikolai Matni

Though this fundamental tradeoff between nominal performance and robustness is known to exist, it is not well-characterized in quantitative terms.

Learning to Control Linear Systems can be Hard

no code implementations27 May 2022 Anastasios Tsiamis, Ingvar Ziemann, Manfred Morari, Nikolai Matni, George J. Pappas

In this paper, we study the statistical difficulty of learning to control linear systems.

Risk of Stochastic Systems for Temporal Logic Specifications

no code implementations28 May 2022 Lars Lindemann, Lejun Jiang, Nikolai Matni, George J. Pappas

For discrete-time stochastic processes, we show under which conditions the approximate STL robustness risk can even be computed exactly.

Autonomous Driving

TaSIL: Taylor Series Imitation Learning

1 code implementation30 May 2022 Daniel Pfrommer, Thomas T. C. K. Zhang, Stephen Tu, Nikolai Matni

We propose Taylor Series Imitation Learning (TaSIL), a simple augmentation to standard behavior cloning losses in the context of continuous control.

Continuous Control Imitation Learning

Toward Certified Robustness Against Real-World Distribution Shifts

1 code implementation8 Jun 2022 Haoze Wu, Teruhiro Tagomori, Alexander Robey, Fengjun Yang, Nikolai Matni, George Pappas, Hamed Hassani, Corina Pasareanu, Clark Barrett

We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts.

How are policy gradient methods affected by the limits of control?

no code implementations14 Jun 2022 Ingvar Ziemann, Anastasios Tsiamis, Henrik Sandberg, Nikolai Matni

We study stochastic policy gradient methods from the perspective of control-theoretic limitations.

Policy Gradient Methods

Statistical Learning Theory for Control: A Finite Sample Perspective

no code implementations12 Sep 2022 Anastasios Tsiamis, Ingvar Ziemann, Nikolai Matni, George J. Pappas

This tutorial survey provides an overview of recent non-asymptotic advances in statistical learning theory as relevant to control and system identification.

Learning Theory

Robust Model Predictive Control of Time-Delay Systems through System Level Synthesis

no code implementations23 Sep 2022 Shaoru Chen, Ning-Yuan Li, Victor M. Preciado, Nikolai Matni

In the proposed method, a time-varying feedback control policy is optimized such that the robust satisfaction of all constraints for the closed-loop system is guaranteed.

Model Predictive Control

Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning

no code implementations5 Oct 2022 David Brandfonbrener, Stephen Tu, Avi Singh, Stefan Welker, Chad Boodoo, Nikolai Matni, Jake Varley

We find that by adjusting the data collection process we improve the quality of both the learned value functions and policies over a variety of baseline methods for data collection.

Continuous Control Reinforcement Learning (RL)

Distributed Optimal Control of Graph Symmetric Systems via Graph Filters

1 code implementation28 Oct 2022 Fengjun Yang, Fernando Gama, Somayeh Sojoudi, Nikolai Matni

Designing distributed optimal controllers subject to communication constraints is a difficult problem unless structural assumptions are imposed on the underlying dynamics and information exchange structure, e. g., sparsity, delay, or spatial invariance.

Learning-enhanced Nonlinear Model Predictive Control using Knowledge-based Neural Ordinary Differential Equations and Deep Ensembles

no code implementations24 Nov 2022 Kong Yao Chee, M. Ani Hsieh, Nikolai Matni

We show that the KNODE ensemble provides more accurate predictions and illustrate the efficacy and closed-loop performance of the proposed nonlinear MPC framework using two case studies.

Model Predictive Control

Multi-Task Imitation Learning for Linear Dynamical Systems

no code implementations1 Dec 2022 Thomas T. Zhang, Katie Kang, Bruce D. Lee, Claire Tomlin, Sergey Levine, Stephen Tu, Nikolai Matni

In particular, we consider a setting where learning is split into two phases: (a) a pre-training step where a shared $k$-dimensional representation is learned from $H$ source policies, and (b) a target policy fine-tuning step where the learned representation is used to parameterize the policy class.

Imitation Learning Representation Learning

The Fundamental Limitations of Learning Linear-Quadratic Regulators

no code implementations27 Mar 2023 Bruce D. Lee, Ingvar Ziemann, Anastasios Tsiamis, Henrik Sandberg, Nikolai Matni

We present a local minimax lower bound on the excess cost of designing a linear-quadratic controller from offline data.

valid

The Power of Learned Locally Linear Models for Nonlinear Policy Optimization

no code implementations16 May 2023 Daniel Pfrommer, Max Simchowitz, Tyler Westenbroek, Nikolai Matni, Stephen Tu

A common pipeline in learning-based control is to iteratively estimate a model of system dynamics, and apply a trajectory optimization algorithm - e. g.~$\mathtt{iLQR}$ - on the learned model to minimize a target cost.

Performance-Robustness Tradeoffs in Adversarially Robust Control and Estimation

no code implementations25 May 2023 Bruce D. Lee, Thomas T. C. K. Zhang, Hamed Hassani, Nikolai Matni

In these special cases, we demonstrate that the severity of the tradeoff depends in an interpretable manner upon system-theoretic properties such as the spectrum of the controllability gramian, the spectrum of the observability gramian, and the stability of the system.

Safety Filter Design for Neural Network Systems via Convex Optimization

1 code implementation16 Aug 2023 Shaoru Chen, Kong Yao Chee, Nikolai Matni, M. Ani Hsieh, George J. Pappas

With the increase in data availability, it has been widely demonstrated that neural networks (NN) can capture complex system dynamics precisely in a data-driven manner.

A Tutorial on the Non-Asymptotic Theory of System Identification

no code implementations7 Sep 2023 Ingvar Ziemann, Anastasios Tsiamis, Bruce Lee, Yassir Jedra, Nikolai Matni, George J. Pappas

This tutorial serves as an introduction to recently developed non-asymptotic methods in the theory of -- mainly linear -- system identification.

EvDNeRF: Reconstructing Event Data with Dynamic Neural Radiance Fields

1 code implementation3 Oct 2023 Anish Bhattacharya, Ratnesh Madaan, Fernando Cladera, Sai Vemprala, Rogerio Bonatti, Kostas Daniilidis, Ashish Kapoor, Vijay Kumar, Nikolai Matni, Jayesh K. Gupta

We present EvDNeRF, a pipeline for generating event data and training an event-based dynamic NeRF, for the purpose of faithfully reconstructing eventstreams on scenes with rigid and non-rigid deformations that may be too fast to capture with a standard camera.

Nonasymptotic Regret Analysis of Adaptive Linear Quadratic Control with Model Misspecification

no code implementations29 Dec 2023 Bruce D. Lee, Anders Rantzer, Nikolai Matni

Toward concretely understanding the benefit of pre-training for adaptive control, we study the adaptive linear quadratic control problem in the setting where the learner has prior knowledge of a collection of basis matrices for the dynamics.

Why Change Your Controller When You Can Change Your Planner: Drag-Aware Trajectory Generation for Quadrotor Systems

no code implementations10 Jan 2024 Hanli Zhang, Anusha Srikanthan, Spencer Folk, Vijay Kumar, Nikolai Matni

In this paper, we argue that adapting the trajectory generation component keeping the controller fixed can improve trajectory tracking for quadrotor systems experiencing drag forces.

Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss

no code implementations8 Feb 2024 Ingvar Ziemann, Stephen Tu, George J. Pappas, Nikolai Matni

We show that whenever the topologies of $L^2$ and $\Psi_p$ are comparable on our hypothesis class $\mathscr{F}$ -- that is, $\mathscr{F}$ is a weakly sub-Gaussian class: $\|f\|_{\Psi_p} \lesssim \|f\|_{L^2}^\eta$ for some $\eta\in (0, 1]$ -- the empirical risk minimizer achieves a rate that only depends on the complexity of the class and second order statistics in its leading term.

Learning Theory

Uncertainty-Aware Deployment of Pre-trained Language-Conditioned Imitation Learning Policies

1 code implementation27 Mar 2024 Bo Wu, Bruce D. Lee, Kostas Daniilidis, Bernadette Bucher, Nikolai Matni

Large-scale robotic policies trained on data from diverse tasks and robotic platforms hold great promise for enabling general-purpose robots; however, reliable generalization to new environment conditions remains a major challenge.

Imitation Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.