L4DC 2022

90 papers

Robust Online Control with Model Misspecification

Udaya Ghai, Xinyi Chen, Elad Hazan, Alexandre Megretski

Structure-Preserving Learning Using Gaussian Processes and Variational Integrators

Jan Brüdigam, Martin Schuck, Alexandre Capone, Stefan Sosnowski, Sandra Hirche

Learning Linear Complementarity Systems

Wanxin Jin, Alp Aydinoglu, Mathew Halm, Michael Posa

Adaptive Variants of Optimal Feedback Policies

Brett Lopez, Jean-Jacques Slotine

Generalization Bounded Implicit Learning of Nearly Discontinuous Functions

Bibit Bianchini, Mathew Halm, Nikolai Matni, Michael Posa

Sliding-Seeking Control: Model-Free Optimization with Safety Constraints

Felipe Galarza-Jiménez, Jorge Poveda, Emiliano Dall’Anese

A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis

Thomas Lew, Lucas Janson, Riccardo Bonalli, Marco Pavone

Robust Graph Neural Networks via Probabilistic Lipschitz Constraints

Raghu Arghal, Eric Lei, Shirin Saeedi Bidokhti

Neural Gaits: Learning Bipedal Locomotion via Control Barrier Functions and Zero Dynamics Policies

Ivan Dario Jimenez Rodriguez, Noel Csomay-Shanklin, Yisong Yue, Aaron D. Ames

Control-Tutored Reinforcement Learning: Towards the Integration of Data-Driven and Model-Based Control

Francesco De Lellis, Marco Coraggio, Giovanni Russo, Mirco Musolesi, Mario di Bernardo

Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum

Junhyung Lyle Kim, Panos Toulis, Anastasios Kyrillidis

Safety-Aware Preference-Based Learning for Safety-Critical Control

Ryan Cosner, Maegan Tucker, Andrew Taylor, Kejun Li, Tamas Molnar

Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models

Jose Luis Vazquez Espinoza, Alexander Liniger, Wilko Schwarting, Daniela Rus, Luc Van Gool

On the Heterogeneity of Independent Learning Dynamics in Zero-sum Stochastic Games

Muhammed Sayin, Kemal Cetiner

Safe Autonomous Navigation for Systems with Learned SE(3) Hamiltonian Dynamics

Zhichao Li, Thai Duong, Nikolay Atanasov

Learning Spatio-Temporal Specifications for Dynamical Systems

Suhail Alsalehi, Erfan Aasi, Ron Weiss, Calin Belta

Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks

Ryan Sander, Wilko Schwarting, Tim Seyde, Igor Gilitschenski, Sertac Karaman

Sample Complexity of the Robust LQG Regulator with Coprime Factors Uncertainty

Yifei Zhang, Sourav Ukil, Ephraim Neimand, Serban Sabau, Myron Hohil

ValueNetQP: Learned One-step Optimal Control for Legged Locomotion

Julian Viereck, Avadesh Meduri, Ludovic Righetti

Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approach

Saber Jafarpour, Matthew Abate, Alexander Davydov, Francesco Bullo, Samuel Coogan

Learning Reversible Symplectic Dynamics

Riccardo Valperga, Kevin Webster, Dmitry Turaev, Victoria Klein, Jeroen Lamb

Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?

Yuchen Cui, Scott Niekum, Abhinav Gupta, Vikash Kumar, Aravind Rajeswaran

Barrier Bayesian Linear Regression: Online Learning of Control Barrier Conditions for Safety-Critical Control of Uncertain Systems

Lukas Brunke, Siqi Zhou, Angela P. Schoellig

Optimal Control with Learning on the Fly: System with Unknown Drift

Daniel Gurevich, Debdipta Goswami, Charles L. Fefferman, Clarence W. Rowley

Time Varying Regression with Hidden Linear Dynamics

Horia Mania, Ali Jadbabaie, Devavrat Shah, Suvrit Sra

Adversarially Regularized Policy Learning Guided by Trajectory Optimization

Zhigen Zhao, Simiao Zuo, Tuo Zhao, Ye Zhao

A Piecewise Learning Framework for Control of Unknown Nonlinear Systems with Stability Guarantees

Milad Farsi, Yinan Li, Ye Yuan, Jun Liu

Bounding the Difference Between Model Predictive Control and Neural Networks

Ross Drummond, Stephen Duncan, Mathew Turner, Patricia Pauli, Frank Allgöwer

Accelerating Dynamical System Simulations with Contracting and Physics-Projected Neural-Newton Solvers

Samuel Chevalier, Jochen Stiasny, Spyros Chatzivasileiadis

Data-Driven Chance Constrained Control using Kernel Distribution Embeddings

Adam Thorpe, Thomas Lew, Meeko Oishi, Marco Pavone

Neural Point Process for Learning Spatiotemporal Event Dynamics

Zihao Zhou, Xingyi Yang, Ryan Rossi, Handong Zhao, Rose Yu

Data-Driven Controller Synthesis of Unknown Nonlinear Polynomial Systems via Control Barrier Certificates

Ameneh Nejati, Bingzhuo Zhong, Marco Caccamo, Majid Zamani

Distributed Control using Reinforcement Learning with Temporal-Logic-Based Reward Shaping

Ningyuan Zhang, Wenliang Liu, Calin Belta

Safe Control with Neural Network Dynamic Models

Tianhao Wei, Changliu Liu

Safe Control with Minimal Regret

Andrea Martin, Luca Furieri, Florian Dorfler, John Lygeros, Giancarlo Ferrari-Trecate

Resiliency of Perception-Based Controllers Against Attacks

Amir Khazraei, Henry Pfister, Miroslav Pajic

Learning Distributed Channel Access Policies for Networked Estimation: Data-driven Optimization in the Mean-field Regime

Marcos Vasconcelos

Clustering-based Mode Reduction for Markov Jump Systems

Zhe Du, Necmiye Ozay, Laura Balzano

Sample-based Distributional Policy Gradient

Rahul Singh, Keuntaek Lee, Yongxin Chen

Input-to-State Stable Neural Ordinary Differential Equations with Applications to Transient Modeling of Circuits

Alan Yang, Jie Xiong, Maxim Raginsky, Elyse Rosenbaum

Robust Data-Driven Output Feedback Control via Bootstrapped Multiplicative Noise

Benjamin Gravell, Iman Shames, Tyler Summers

Improving Dynamic Regret in Distributed Online Mirror Descent Using Primal and Dual Information

Nima Eshraghi, Ben Liang

Formal Synthesis of Safety Controllers for Unknown Stochastic Control Systems using Gaussian Process Learning

Rameez Wajid, Asad Ullah Awan, Majid Zamani

Block Contextual MDPs for Continual Learning

Shagun Sodhani, Franziska Meier, Joelle Pineau, Amy Zhang

Adaptive Stochastic MPC under Unknown Noise Distribution

Charis Stamouli, Anastasios Tsiamis, Manfred Morari, George J. Pappas

Symplectic Momentum Neural Networks - Using Discrete Variational Mechanics as a prior in Deep Learning

Saul Santos, Monica Ekal, Rodrigo Ventura

Distributed Neural Network Control with Dependability Guarantees: a Compositional Port-Hamiltonian Approach

Luca Furieri, Clara Lucía Galimberti, Muhammad Zakwan, Giancarlo Ferrari-Trecate

Reinforcement Learning with Almost Sure Constraints

Agustin Castellano, Hancheng Min, Enrique Mallada, Juan Andrés Bazerque

Dynamic Learning of Correlation Potentials for a Time-Dependent Kohn-Sham System

Harish S. Bhat, Kevin Collins, Prachi Gupta, Christine M. Isborn

Adversarially Robust Stability Certificates can be Sample-Efficient

Thomas Zhang, Stephen Tu, Nicholas Boffi, Jean-Jacques Slotine, Nikolai Matni

Total Energy Shaping with Neural Interconnection and Damping Assignment - Passivity Based Control

Santiago Sanchez-Escalonilla Plaza, Rodolfo Reyes-Baez, Bayu Jayawardhana

Diffeomorphic Transforms for Generalised Imitation Learning

Weiming Zhi, Tin Lai, Lionel Ott, Fabio Ramos

MyoSuite: A Contact-rich Simulation Suite for Musculoskeletal Motor Control

Vittorio Caggiano, Huawei Wang, Guillaume Durandau, Massimo Sartori, Vikash Kumar

Adaptive Model Predictive Control by Learning Classifiers

Rel Guzman, Rafael Oliveira, Fabio Ramos

Data-driven Control of Unknown Linear Systems via Quantized Feedback

Feiran Zhao, Xingchen Li, Keyou You

Learning to Reach, Swim, Walk and Fly in One Trial: Data-Driven Control with Scarce Data and Side Information

Franck Djeumou, Ufuk Topcu

Data-Driven Safety Verification of Stochastic Systems via Barrier Certificates: A Wait-and-Judge Approach

Ali Salamati, Majid Zamani

Learning Linear Models Using Distributed Iterative Hessian Sketching

Han Wang, James Anderson

Mixtures of Controlled Gaussian Processes for Dynamical Modeling of Deformable Objects

Ce Xu Zheng, Adrià Colomé, Luis Sentis, Carme Torras

Online Estimation and Control with Optimal Pathlength Regret

Gautam Goel, Babak Hassibi

Gradient and Projection Free Distributed Online Min-Max Resource Optimization

Jingrong Wang, Ben Liang

Data-Augmented Contact Model for Rigid Body Simulation

Yifeng Jiang, Jiazheng Sun, C. Karen Liu

Traversing Time with Multi-Resolution Gaussian Process State-Space Models

Krista Longi, Jakob Lindinger, Olaf Duennbier, Melih Kandemir, Arto Klami

Optimal Pointing Sequences in Spacecraft Formation Flying Using Online Planning with Resource Constraints

Samuel Low, Mykel Kochenderfer

Distributed Stochastic Nash Equilibrium Learning in Locally Coupled Network Games with Unknown Parameters

Yuanhanqing Huang, Jianghai Hu

Learning POMDP Models with Similarity Space Regularization: a Linear Gaussian Case Study

Yujie Yang, Jianyu Chen, Shengbo Li

Vision-based System Identification and 3D Keypoint Discovery using Dynamics Constraints

Miguel Jaques, Martin Asenov, Michael Burke, Timothy Hospedales

Accelerating Model-Free Policy Optimization Using Model-Based Gradient: A Composite Optimization Perspective

Yansong Li, Shuo Han

Safe Reinforcement Learning with Chance-constrained Model Predictive Control

Samuel Pfrommer, Tanmay Gautam, Alec Zhou, Somayeh Sojoudi

Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees

Siliang Zeng, Tianyi Chen, Alfredo Garcia, Mingyi Hong

Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modeling

Franck Djeumou, Cyrus Neary, Eric Goubault, Sylvie Putot, Ufuk Topcu

i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery

Cameron R. Wolfe, Anastasios Kyrillidis

Data-Enabled Gradient Flow as Feedback Controller: Regulation of Linear Dynamical Systems to Minimizers of Unknown Functions

Liliaokeawawa Cothren, Gianluca Bianchin, Emiliano Dall’Anese

Training Lipschitz Continuous Operators Using Reproducing Kernels

Henk van Waarde, Rodolphe Sepulchre

Certified Robustness via Locally Biased Randomized Smoothing

Brendon G. Anderson, Somayeh Sojoudi

Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems

Thinh Doan

On the Sample Complexity of Stability Constrained Imitation Learning

Stephen Tu, Alexander Robey, Tingnan Zhang, Nikolai Matni

Online No-regret Model-Based Meta RL for Personalized Navigation

Yuda Song, Yuan Ye, Wen Sun, Kris Kitani

Learning-based Moving Horizon Estimation through Differentiable Convex Optimization Layers

Simon Muntwiler, Kim P. Wabersich, Melanie N. Zeilinger

OpReg-Boost: Learning to Accelerate Online Algorithms with Operator Regression

Nicola Bastianello, Andrea Simonetto, Emiliano Dall’Anese

Tracking and Planning with Spatial World Models

Baris Kayalibay, Atanas Mirchev, Patrick van der Smagt, Justin Bayer

Experience Replay with Likelihood-free Importance Weights

Samarth Sinha, Jiaming Song, Animesh Garg, Stefano Ermon

Joint Synthesis of Safety Certificate and Safe Control Policy Using Constrained Reinforcement Learning

Haitong Ma, Changliu Liu, Shengbo Eben Li, Sifa Zheng, Jianyu Chen

Learning-Enabled Robust Control with Noisy Measurements

Olle Kjellqvist, Anders Rantzer

Noise Handling in Data-driven Predictive Control: A Strategy Based on Dynamic Mode Decomposition

Andrea Sassella, Valentina Breschi, Simone Formentin

Modeling Partially Observable Systems using Graph-Based Memory and Topological Priors

Steven Morad, Stephan Liwicki, Ryan Kortvelesy, Roberto Mecca, Amanda Prorok

On the Effectiveness of Iterative Learning Control

Anirudh Vemula, Wen Sun, Maxim Likhachev, J. Andrew Bagnell

PRISM: Recurrent Neural Networks and Presolve Methods for Fast Mixed-integer Optimal Control

Abhishek Cauligi, Ankush Chakrabarty, Stefano Di Cairano, Rien Quirynen

PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems

Ting-Han Fan, Xian Yeow Lee, Yubo Wang

Automated Design of Grey-Box Recurrent Neural Networks For Fault Diagnosis using Structural Models and Causal Information

Daniel Jung