mlsanityData to 7 Oct 2026

Safe and Reliable Training of Learning-Based Aerospace Controllers

arXiv 2407.07088 ↗First posted 9 Jul 2024cs.AI cs.LO cs.SYcited by 4

Not on the map. Why?

Abstract (arXiv)

In recent years, deep reinforcement learning (DRL) approaches have generated highly successful controllers for a myriad of complex domains. However, the opaque nature of these models limits their applicability in aerospace systems and safety-critical domains, in which a single mistake can have dire consequences. In this paper, we present novel advancements in both the training and verification of DRL controllers, which can help ensure their safe behavior. We showcase a design-for-verification approach utilizing k-induction and demonstrate its use in verifying liveness properties. In addition, we also give a brief overview of neural Lyapunov Barrier certificates and summarize their capabilities on a case study. Finally, we describe several other novel reachability-based approaches which, despite failing to provide guarantees of interest, could be effective for verification of other DRL systems, and could be of further interest to the community.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 52 of its 75 references that are in the map. First posted on arXiv 9 Jul 2024.

Builds on

52 of 75 references.

References · 52

  1. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  2. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  3. 2019Control Barrier Functions: Theory and Applicationscited by 332
  4. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 278
  5. 2016Safety Verification of Deep Neural Networkscited by 262
  6. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 261
  7. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  8. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 186
  9. 2022Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methodscited by 148
  10. 2020Neural Lyapunov Controlcited by 142
  11. 2017An approach to reachability analysis for feed-forward ReLU neural networkscited by 126
  12. 2021Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functionscited by 91
38 more
  1. 2018Verisig: verifying safety properties of hybrid systems with neural network controllerscited by 83
  2. 2024Marabou 2.0: A Versatile Formal Analyzer of Neural Networkscited by 81
  3. 2021Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificatescited by 71
  4. 2019An Abstraction-Based Framework for Neural Network Verificationcited by 68
  5. 2022Reachability Constrained Reinforcement Learningcited by 52
  6. 2020An SMT-Based Approach for Verifying Binarized Neural Networkscited by 47
  7. 2021Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learningcited by 43
  8. 2014Reach-Avoid Problems with Time-Varying Dynamics, Targets and Constraintscited by 41
  9. 2019Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustnesscited by 40
  10. 2021Neural Network Robustness as a Verification Property: A Principled Case Studycited by 35
  11. 2020Abstraction based Output Range Analysis for Neural Networkscited by 34
  12. 2021Towards Scalable Verification of Deep Reinforcement Learningcited by 33
  13. 2021Stabilizing Neural Control Using Self-Learned Almost Lyapunov Criticscited by 33
  14. 2022Verifying Learning-Based Robotic Navigation Systemscited by 33
  15. 2023Iterative Reachability Estimation for Safe Reinforcement Learningcited by 33
  16. 2016Robustness of Control Barrier Functions for Safety Critical Controlcited by 29
  17. 2021NNrepair: Constraint-based Repair of Neural Network Classifierscited by 24
  18. 2022An Abstraction-Refinement Approach to Verifying Convolutional Neural Networkscited by 24
  19. 2023Solving Stabilize-Avoid Optimal Control via Epigraph Form and Deep Reinforcement Learningcited by 24
  20. 2023Formally Explaining Neural Networks within Reactive Systemscited by 24
  21. 2019Exploring applications of deep reinforcement learning for real-world autonomous driving systemscited by 18
  22. 2022Verification-Aided Deep Ensemble Selectioncited by 18
  23. 2022Neural Network Verification using Residual Reasoningcited by 18
  24. 2022Enforcing safety for vision-based controllers via Control Barrier Functions and Neural Radiance Fieldscited by 15
  25. 2024Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificatescited by 15
  26. 2024Verification-Guided Shielding for Deep Reinforcement Learningcited by 13
  27. 2018Toward Scalable Verification for Safety-Critical Deep Networkscited by 12
  28. 2024Shield Synthesis for LTL Modulo Theoriescited by 12
  29. 2019A Reachability Method for Verifying Dynamical Systems with Deep Neural Network Controllerscited by 11
  30. 2023Verifying Generalization in Deep Learningcited by 11
  31. 2020Formal Methods with a Touch of Magiccited by 10
  32. 2022Quantifying Safety of Learning-based Self-Driving Control Using Almost-Barrier Functionscited by 10
  33. 2023Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Modelscited by 10
  34. 2022Tighter Abstract Queries in Neural Network Verificationcited by 8
  35. 2023Sequential Neural Barriers for Scalable Dynamic Obstacle Avoidancecited by 8
  36. 2024Analyzing Adversarial Inputs in Deep Reinforcement Learningcited by 7
  37. 2023A General Framework for Verification and Control of Dynamical Models via Certificate Synthesiscited by 6
  38. 2019Incremental Bounded Model Checking of Artificial Neural Networks in CUDAcited by 3

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretationcited by 11
  2. 2026Defining Operational Conditions for Safety-Critical AI-Based Systems from Datacited by 1
  3. 2025On Improving Deep Active Learning with Formal Verificationcited by 0
  4. 2026Neural Network Verification using Partial Multi-Neuron Relaxationcited by 0