Copertina

Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Frauenknecht, Bernd, Kesper, Lukas, Mayfrank, Daniel, Hose, Henrik, Trimpe, Sebastian
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Systems and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Retraining
di: Hose, Henrik, et al.
Pubblicazione: (2024)

Feedforward Controllers from Learned Dynamic Local Model Networks with Application to Excavator Assistance Functions
di: Greiser, Leon, et al.
Pubblicazione: (2024)

Approximate non-linear model predictive control with safety-augmented neural networks
di: Hose, Henrik, et al.
Pubblicazione: (2023)

End-to-End Reinforcement Learning of Koopman Models for Economic Nonlinear Model Predictive Control
di: Mayfrank, Daniel, et al.
Pubblicazione: (2023)

Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
di: Eisele, Artur, et al.
Pubblicazione: (2026)

The Mini Wheelbot: A Testbed for Learning-based Balancing, Flips, and Articulated Driving
di: Hose, Henrik, et al.
Pubblicazione: (2025)

Safety in safe Bayesian optimization and its ramifications for control
di: Fiedler, Christian, et al.
Pubblicazione: (2025)

Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Space Models
di: Berger, Julia, et al.
Pubblicazione: (2026)

The Mini Wheelbot Dataset: High-Fidelity Data for Robot Learning
di: Hose, Henrik, et al.
Pubblicazione: (2026)

Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption
di: Frauenknecht, Bernd, et al.
Pubblicazione: (2024)

Beyond Prediction: Interval Neural Networks for Uncertainty-Aware System Identification
di: Ferah, Mehmet Ali, et al.
Pubblicazione: (2026)

Dynamic Origin-Destination Matrix Prediction with Line Graph Neural Networks and Kalman Filter
di: Xiong, Xi, et al.
Pubblicazione: (2019)

Fine-Tuning of Neural Network Approximate MPC without Retraining via Bayesian Optimization
di: Hose, Henrik, et al.
Pubblicazione: (2025)

Domain-decoupled Physics-informed Neural Networks with Closed-form Gradients for Fast Model Learning of Dynamical Systems
di: Krauss, Henrik, et al.
Pubblicazione: (2024)

Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures
di: Seo, Junwon, et al.
Pubblicazione: (2025)

Local Bayesian Optimization for Controller Tuning with Crash Constraints
di: von Rohr, Alexander, et al.
Pubblicazione: (2024)

Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot
di: Subhasish, Devdutt, et al.
Pubblicazione: (2026)

Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors
di: Cramer, Emma, et al.
Pubblicazione: (2024)

On Rollouts in Model-Based Reinforcement Learning
di: Frauenknecht, Bernd, et al.
Pubblicazione: (2025)

Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control
di: Saviolo, Alessandro, et al.
Pubblicazione: (2022)

Automatic nonlinear MPC approximation with closed-loop guarantees
di: Tokmak, Abdullah, et al.
Pubblicazione: (2023)

Adaptive Model-Predictive Control of a Soft Continuum Robot Using a Physics-Informed Neural Network Based on Cosserat Rod Theory
di: Licher, Johann, et al.
Pubblicazione: (2025)

Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF
di: Holtmann, Tobin, et al.
Pubblicazione: (2025)

Safe Value Functions
di: Massiani, Pierre-François, et al.
Pubblicazione: (2021)

Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agents
di: Bejarano, Federico Pizarro, et al.
Pubblicazione: (2024)

Assumed Density Filtering and Smoothing with Neural Network Surrogate Models
di: Kuang, Simon, et al.
Pubblicazione: (2025)

Safe and Stable Closed-Loop Learning for Neural-Network-Supported Model Predictive Control
di: Hirt, Sebastian, et al.
Pubblicazione: (2024)

LUCID: Learning-Enabled Uncertainty-Aware Certification of Stochastic Dynamical Systems
di: Casablanca, Ernesto, et al.
Pubblicazione: (2025)

Data-Driven Observability Analysis for Nonlinear Stochastic Systems
di: Massiani, Pierre-François, et al.
Pubblicazione: (2023)

Simulation-Aided Policy Tuning for Black-Box Robot Learning
di: He, Shiming, et al.
Pubblicazione: (2024)

Constraint-Aware Refinement for Safety Verification of Neural Feedback Loops
di: Rober, Nicholas, et al.
Pubblicazione: (2024)

Component-Aware Pruning Framework for Neural Network Controllers via Gradient-Based Importance Estimation
di: Sundaram, Ganesh, et al.
Pubblicazione: (2026)

System-level Safety Guard: Safe Tracking Control through Uncertain Neural Network Dynamics Models
di: Li, Xiao, et al.
Pubblicazione: (2023)

High-Dimensional Surrogate Modeling for Closed-Loop Learning of Neural-Network-Parameterized Model Predictive Control
di: Hirt, Sebastian, et al.
Pubblicazione: (2025)

Breaking Free: Decoupling Forced Systems with Laplace Neural Networks
di: Zimmering, Bernd, et al.
Pubblicazione: (2025)

Statistically Assuring Safety of Control Systems using Ensembles of Safety Filters and Conformal Prediction
di: Tabbara, Ihab, et al.
Pubblicazione: (2025)

Sample-Free Safety Assessment of Neural Network Controllers via Taylor Methods
di: Evans, Adam, et al.
Pubblicazione: (2026)

Provably Optimal Reinforcement Learning under Safety Filtering
di: Oh, Donggeon David, et al.
Pubblicazione: (2025)

Efficient Interaction-Aware Interval Analysis of Neural Network Feedback Loops
di: Jafarpour, Saber, et al.
Pubblicazione: (2023)

Discrete-time Contraction-based Control of Nonlinear Systems with Parametric Uncertainties using Neural Networks
di: Wei, Lai, et al.
Pubblicazione: (2021)