mlsanityData to 7 Oct 2026

Safety Filter Design for Neural Network Systems via Convex Optimization

arXiv 2308.08086 ↗First posted 16 Aug 2023eess.SY cs.LG cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

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. However, the architectural complexity and nonlinearity of the NNs make it challenging to synthesize a provably safe controller. In this work, we propose a novel safety filter that relies on convex optimization to ensure safety for a NN system, subject to additive disturbances that are capable of capturing modeling errors. Our approach leverages tools from NN verification to over-approximate NN dynamics with a set of linear bounds, followed by an application of robust linear MPC to search for controllers that can guarantee robust constraint satisfaction. We demonstrate the efficacy of the proposed framework numerically on a nonlinear pendulum system.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 16 Aug 2023.

Builds on

27 of 43 references.

References · 27

  1. 2016OpenAI Gymcited by 1,684
  2. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  3. 2017Safe Reinforcement Learning via Shieldingcited by 427
  4. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  5. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  6. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 261
  7. 2018Differentiable MPC for End-to-end Planning and Controlcited by 178
  8. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 150
  9. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 91
  10. 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 80
  11. 2019Data Efficient Reinforcement Learning for Legged Robotscited by 60
  12. 2021Safe Reinforcement Learning Using Robust Control Barrier Functionscited by 44
15 more
  1. 2021NeuroBEM: Hybrid Aerodynamic Quadrotor Modelcited by 33
  2. 2021KNODE-MPC: A Knowledge-based Data-driven Predictive Control Framework for Aerial Robotscited by 26
  3. 2021Run Time Assurance for Safety-Critical Systems: An Introduction to Safety Filtering Approaches for Complex Control Systemscited by 25
  4. 2021A predictive safety filter for learning-based racing controlcited by 17
  5. 2022Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Trackingcited by 16
  6. 2016Learning Quadrotor Dynamics Using Neural Network for Flight Controlcited by 15
  7. 2016Nonlinear Systems Identification Using Deep Dynamic Neural Networkscited by 14
  8. 2021Predictive control barrier functions: Enhanced safety mechanisms for learning-based controlcited by 13
  9. 2019Linear robust adaptive model predictive control: Computational complexity and conservatism -- extended versioncited by 8
  10. 2022Learning Differentiable Safety-Critical Control using Control Barrier Functions for Generalization to Novel Environmentscited by 8
  11. 2023Robust Nonlinear Optimal Control via System Level Synthesiscited by 7
  12. 2022Robust Model Predictive Control with Polytopic Model Uncertainty through System Level Synthesiscited by 6
  13. 2022Predictive safety filter using system level synthesiscited by 6
  14. 2019System Level Synthesiscited by 3
  15. 2022Robust Model Predictive Control of Time-Delay Systems through System Level Synthesiscited by 2

Built on by

Not cited yet.