Top Tweets for #DataDrivenControl

23 days ago

📢 Call for Papers | Special Issue in Computation 👤 Guest Editor: Mehran Bahmani 📅 Submission deadline: 31 May 2027 🔗 Learn more and submit your manuscript: https://t.co/o4sh4Alqoc #Computation #KoopmanOperator #DataDrivenControl

ComputationMDPI's tweet photo. 📢 Call for Papers | Special Issue in Computation

👤 Guest Editor: Mehran Bahmani

📅 Submission deadline: 31 May 2027

🔗 Learn more and submit your manuscript:
https://t.co/o4sh4Alqoc

#Computation #KoopmanOperator #DataDrivenControl https://t.co/QlfgzRmwsM

Control Theory and Technology @CTT_Journal

about 1 month ago

[Series 5 | Machine Learning & Data-Driven Control | #6] #AutonomousVehicles #ReinforcementLearning #EnergyEfficiency #DataDrivenControl 🚗⚡ How can autonomous driving be made more energy-efficient in urban environments? This work leverages Proximal Policy Optimization (PPO) to optimize driving behaviors at traffic signals, on-ramps, and in dense traffic, achieving improved energy efficiency. Title: Design of energy-saving driving strategy based on proximal policy optimization considering urban transport information Authors: Qifang Liu, Dazhen Sun, Haowen Chen, Dongzi Li & Ping Wang Full Text: https://t.co/7cD8z3XaOr

CTT_Journal's tweet photo. [Series 5 | Machine Learning & Data-Driven Control | #6]
#AutonomousVehicles #ReinforcementLearning #EnergyEfficiency #DataDrivenControl
🚗⚡ How can autonomous driving be made more energy-efficient in urban environments?
This work leverages Proximal Policy Optimization (PPO) to optimize driving behaviors at traffic signals, on-ramps, and in dense traffic, achieving improved energy efficiency.

Title: Design of energy-saving driving strategy based on proximal policy optimization considering urban transport information
Authors: Qifang Liu, Dazhen Sun, Haowen Chen, Dongzi Li & Ping Wang
Full Text: https://t.co/7cD8z3XaOr

Control Theory and Technology @CTT_Journal

about 1 month ago

[Series 5 | Machine Learning & Data-Driven Control | #5] #NeuralNetworks #ControlSystems #DeepLearning #DataDrivenControl 🧠⚖️ Can neural networks outperform traditional model-based controllers? This comparative study shows that feedforward and recurrent neural networks can surpass original analytical controller designs in overall control performance. 📝📝 Title: Application of feedforward and recurrent neural networks for model-based control systems Authors: Marek Krok, Wojciech P. Hunek, Szymon Mielczarek, Filip Buchwald, Adam Kolender Full text: https://‍https://t.co/7V3FXoFgGU

CTT_Journal's tweet photo. [Series 5 | Machine Learning & Data-Driven Control | #5]
#NeuralNetworks #ControlSystems #DeepLearning #DataDrivenControl
🧠⚖️
Can neural networks outperform traditional model-based controllers?
This comparative study shows that feedforward and recurrent neural networks can surpass original analytical controller designs in overall control performance.

📝📝
Title: Application of feedforward and recurrent neural networks for model-based control systems
Authors: Marek Krok, Wojciech P. Hunek, Szymon Mielczarek, Filip Buchwald, Adam Kolender
Full text: https://‍https://t.co/7V3FXoFgGU

Control Theory and Technology @CTT_Journal

about 1 month ago

[Series 5 | Machine Learning & Data-Driven Control | #4] #NeuralNetworks #OptimalControl #ReinforcementLearning #DataDrivenControl 🧠⚙️ How can we build a self-learning controller for unknown multi-input systems? This work develops a data-based adaptive neural dynamic programming approach with integral reinforcement, avoiding the need to solve complex HJB equations. Title: Data-based neural controls for an unknown continuous-time multi-input system with integral reinforcement Authors: Yongfeng Lv, Jun Zhao, Wan Zhang, Huimin Chang Full Text: https://t.co/W6sEKJi1Ho

CTT_Journal's tweet photo. [Series 5 | Machine Learning & Data-Driven Control | #4]
#NeuralNetworks #OptimalControl #ReinforcementLearning #DataDrivenControl
🧠⚙️ How can we build a self-learning controller for unknown multi-input systems?
This work develops a data-based adaptive neural dynamic programming approach with integral reinforcement, avoiding the need to solve complex HJB equations.

Title: Data-based neural controls for an unknown continuous-time multi-input system with integral reinforcement
Authors: Yongfeng Lv, Jun Zhao, Wan Zhang, Huimin Chang
Full Text: https://t.co/W6sEKJi1Ho

Control Theory and Technology @CTT_Journal

about 1 month ago

[Series 5 | Machine Learning & Data-Driven Control | #3] #DataDrivenControl #LQR #OptimalControl #MachineLearning 📉🎯 Can optimal controllers be designed with far less experimental data? This work proposes a data-driven LQR method that reduces the required data amount by half, while maintaining strong control performance. 🧐🧐🧐 Title: Reduction of data amount in data-driven design of linear quadratic regulators Authors: Shinsaku Izumi, Xin Xin More at: https://t.co/hxlO3AoEBs

CTT_Journal's tweet photo. [Series 5 | Machine Learning & Data-Driven Control | #3]
#DataDrivenControl #LQR #OptimalControl #MachineLearning
📉🎯 Can optimal controllers be designed with far less experimental data?
This work proposes a data-driven LQR method that reduces the required data amount by half, while maintaining strong control performance.

🧐🧐🧐
Title: Reduction of data amount in data-driven design of linear quadratic regulators
Authors: Shinsaku Izumi, Xin Xin
More at: https://t.co/hxlO3AoEBs

Solmaz Kia @Solmaz_S_Kia

about 2 months ago

Sharing our recent work, “SCALARFEDLQR: Scalar Federated Learning for Linear Quadratic Regulator”, led by my PhD student M. Reza Rostami, with collaboration from Shahriar Talebi (UCLA). ArXiv link: https://t.co/GlyI3fxZqL #LQR #DataDrivenControl #FederatedLearning #EmbeddedAI

Solmaz_S_Kia's tweet photo. Sharing our recent work, “SCALARFEDLQR: Scalar Federated Learning for Linear Quadratic Regulator”, led by my PhD student M. Reza Rostami, with collaboration from Shahriar Talebi (UCLA).

ArXiv link: https://t.co/GlyI3fxZqL

#LQR #DataDrivenControl #FederatedLearning #EmbeddedAI https://t.co/fAQWcCyKmF

Robotics @Robotics201

5 months ago

Fast data-driven iterative learning control for linear system with output disturbance #DataDrivenControl #ControlTheory #LinearSystems #OutputDisturbance International Robotics and Automation Awards Visit Us: https://t.co/tsUXfhL8k8 Nomination:https://t.co/SHfgLi28AO

Control Theory and Technology @CTT_Journal

5 months ago

📘 Distributed & Data-Driven Optimization CTT Regular Issues 2023–2024 – Part II: Advanced Control Theory and Methods #ControlTheory #Optimization #DistributedSystems #DataDrivenControl This set of papers formulates control-related problems explicitly in the framework of optimization, covering online decision-making, gradient-free optimization, data-driven LQR design, and sparse model identification under practical constraints. 🔹 Distributed regularized online optimization using forward–backward splitting (Yuan et al., 2023) Proposes a distributed forward–backward splitting algorithm with fixed and adaptive step sizes, achieving regret bounds comparable to centralized methods. 🔗 Full Text: https://t.co/nsJIq2bb3T 🔹 Random gradient-free method for online distributed optimization with strongly pseudoconvex cost functions (Yan et al., 2024) Develops a gradient-free distributed algorithm based on multi-point estimators, with sublinear expected dynamic regret under time-varying objectives. 🔗 Full Text: https://t.co/PKvQidFKmd 🔹 Reduction of data amount in data-driven design of linear quadratic regulators (Izumi & Xin, 2024) Introduces a simplified data-driven LQR design that significantly reduces required experimental data, with analysis under measurement noise. 🔗 Full Text: https://t.co/Jhucx4au8t 🔹 Variable projection algorithms with sparse constraint for separable nonlinear models (Xu et al., 2024) Presents gradient- and trust-region-based variable projection methods that handle sparsity constraints in separable nonlinear model identification. 🔗 Full Text: https://t.co/sV4rEP3WMk 💡 These papers explore how optimization-based and data-driven methods can be leveraged to address distributed, online, and data-limited control problems.

CTT_Journal's tweet photo. 📘 Distributed & Data-Driven Optimization

CTT Regular Issues 2023–2024 – Part II: Advanced Control Theory and Methods
#ControlTheory #Optimization #DistributedSystems #DataDrivenControl

This set of papers formulates control-related problems explicitly in the framework of optimization, covering online decision-making, gradient-free optimization, data-driven LQR design, and sparse model identification under practical constraints.

🔹 Distributed regularized online optimization using forward–backward splitting (Yuan et al., 2023)
Proposes a distributed forward–backward splitting algorithm with fixed and adaptive step sizes, achieving regret bounds comparable to centralized methods.
🔗 Full Text: https://t.co/nsJIq2bb3T

🔹 Random gradient-free method for online distributed optimization with strongly pseudoconvex cost functions (Yan et al., 2024)
Develops a gradient-free distributed algorithm based on multi-point estimators, with sublinear expected dynamic regret under time-varying objectives.
🔗 Full Text: https://t.co/PKvQidFKmd

🔹 Reduction of data amount in data-driven design of linear quadratic regulators (Izumi & Xin, 2024)
Introduces a simplified data-driven LQR design that significantly reduces required experimental data, with analysis under measurement noise.
🔗 Full Text: https://t.co/Jhucx4au8t

🔹 Variable projection algorithms with sparse constraint for separable nonlinear models (Xu et al., 2024)
Presents gradient- and trust-region-based variable projection methods that handle sparsity constraints in separable nonlinear model identification.
🔗 Full Text: https://t.co/sV4rEP3WMk

💡 These papers explore how optimization-based and data-driven methods can be leveraged to address distributed, online, and data-limited control problems.

Researchhires @researchhires

6 months ago

PhD Student in Automatic Control 📍Linköping, Sweden Apply now: https://t.co/paGnrz09Oh #PhD #AutomaticControl #Sweden #ResearchHires #DataDrivenControl #Robotics #AutonomousSystems

R. Alessio @ ETH | RL, Bandits, Exploration

@rssalessio

7 months ago

80⭐️ on a tiny repo on data-driven control I put out during my PhD! PyDeePC is a tiny Python implementation of Data-enabled Predictive Control. It is model-free, quick to try, easy to learn. Feedback welcome! https://t.co/xSqEOd6p8b #MPC #ControlTheory #DataDrivenControl

rssalessio's tweet photo. 80⭐️ on a tiny repo on data-driven control I put out during my PhD!

PyDeePC is a tiny Python implementation of Data-enabled Predictive Control. It is model-free, quick to try, easy to learn. Feedback welcome!

https://t.co/xSqEOd6p8b
#MPC #ControlTheory #DataDrivenControl https://t.co/fhbJkstzfT

207

IEEE Open Journal of Control Systems @IEEE_OJCSYS

8 months ago

"Cautious Optimization via Data Informativity," by Jaap Eising; Jorge Cortés Date: 22 Sept 2025 Link: https://t.co/qgnNgudx3N #optimization #nonlinearsystems #noise #datadrivencontrol #controlsystems #ojcsys

IEEE_OJCSYS's tweet photo. "Cautious Optimization via Data Informativity," by Jaap Eising; Jorge Cortés
Date: 22 Sept 2025
Link: https://t.co/qgnNgudx3N #optimization #nonlinearsystems #noise #datadrivencontrol #controlsystems #ojcsys https://t.co/mbtZchDy1g

Energies MDPI @energies_mdpi

9 months ago

📚 #CallForReading Explore the Special Issue "Power Electronic Converter and Its Control". 👉 https://t.co/47kHiuu2vu #RobustPredictiveControl #MPC #DataDrivenControl #ModelessControl #PredictiveControl #AIinControl #ArtificialIntelligence #mdpienergies #openaccess

energies_mdpi's tweet photo. 📚 #CallForReading Explore the Special Issue "Power Electronic Converter and Its Control".

👉 https://t.co/47kHiuu2vu

#RobustPredictiveControl #MPC #DataDrivenControl #ModelessControl #PredictiveControl #AIinControl #ArtificialIntelligence

#mdpienergies #openaccess https://t.co/yOeOVcvwZ6

Robotics @Robotics201

12 months ago

Data-driven control against false data injection attacks #DataDrivenControl #SmartSecurity #CyberDefense #AIForCybersecurity International Robotics and Automation Awards Visit Us:https://t.co/tsUXfhL8k8 Nomination:https://t.co/SHfgLi28AO

Santosh Rajkumar @smrajkumar

about 1 year ago

Need to control nonlinear systems from partial data? Our Koopman-based bilinear HMM (trained via neural EM) drives output regulation & MPC—no physics needed. See you at #ACC2025! #DataDrivenControl #KoopmanOperators #MPC #SciML

smrajkumar's tweet photo. Need to control nonlinear systems from partial data? Our Koopman-based bilinear HMM (trained via neural EM) drives output regulation & MPC—no physics needed. See you at #ACC2025!

#DataDrivenControl #KoopmanOperators #MPC #SciML https://t.co/54Jtc3qxXk

179

Energies MDPI @energies_mdpi

over 2 years ago

#mdpienergies #callforreading 👏 We are happy to invite you to read Special Issue "Intelligent Control for Future Systems". 👉 https://t.co/J2az4Ozz1f #intelligentcontrol #computationalintelligence #datadrivencontrol #nonlinearcontrolsystems #fractionalordersystems

$energies_mdpi's tweet photo. #mdpienergies #callforreading 👏 We are happy to invite you to read Special Issue "Intelligent Control for Future Systems". 👉 https://t.co/J2az4Ozz1f #intelligentcontrol #computationalintelligence #datadrivencontrol #nonlinearcontrolsystems #fractionalordersystems https://t.co/1BLCKJVQWc$

Bulletpapers - Daily Research Papers, Summarized @bulletpapers

over 2 years ago

New data-driven approach controls complex systems without models, using only input-output data. Maximizes stability & handles nonlinear dynamics better than traditional methods. #DataDrivenControl #ComplexSystems #ML Read more: https://t.co/VFh9rt0f9G

ACC2026 @ACC_Control

about 3 years ago

📢 Tutorial 3 at #ACC2023: Data-Driven Control Organizers: 🔸 Anuradha Annaswamy, MIT 🔸 Yan Wang, Ford Research & Advanced Engineering Explore the history & recent advances in data-driven control! #ControlSystems #DataDrivenControl #Engineering