mlsanityData to 7 Oct 2026

Discrete-Event Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components

arXiv 2202.03360 ↗First posted 7 Feb 2022cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

We present DeepDECS, a new method for the synthesis of correct-by-construction discrete-event controllers for autonomous systems that use deep neural network (DNN) classifiers for the perception step of their decision-making processes. Despite major advances in deep learning in recent years, providing safety guarantees for these systems remains very challenging. Our controller synthesis method addresses this challenge by integrating DNN verification with the synthesis of verified Markov models. The synthesised models correspond to discrete-event controllers guaranteed to satisfy the safety, dependability and performance requirements of the autonomous system, and to be Pareto optimal with respect to a set of optimisation objectives. We use the method in simulation to synthesise controllers for mobile-robot collision mitigation and for maintaining driver attentiveness in shared-control autonomous driving.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 21 of its 47 references that are in the map. First posted on arXiv 7 Feb 2022.

Builds on

21 of 47 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
  5. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 278
  6. 2016Safety Verification of Deep Neural Networkscited by 262
  7. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  8. 2021Globally-Robust Neural Networkscited by 106
  9. 2020Multivariate Confidence Calibration for Object Detectioncited by 98
  10. 2020The Probabilistic Model Checker Stormcited by 64
  11. 2019Uncertainty Quantification with Statistical Guarantees in End-to-End Autonomous Driving Controlcited by 60
  12. 2018Deep Neural Network Compression for Aircraft Collision Avoidance Systemscited by 58
9 more
  1. 2019Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challengescited by 39
  2. 2021Conformal Bayesian Computationcited by 38
  3. 2019Deep Learning for Large-Scale Traffic-Sign Detection and Recognitioncited by 34
  4. 2020DeepTake: Prediction of Driver Takeover Behavior using Multimodal Datacited by 13
  5. 2014Optimal Cost Almost-sure Reachability in POMDPscited by 12
  6. 2014Qualitative Analysis of POMDPs with Temporal Logic Specifications for Robotics Applicationscited by 8
  7. 2019Detection and Mitigation of Rare Subclasses in Deep Neural Network Classifierscited by 4
  8. 2021Monotonic Safety for Scalable and Data-Efficient Probabilistic Safety Analysiscited by 3
  9. 2021Maintaining driver attentiveness in shared-control autonomous drivingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 1; 2026: 1.

5 papers.

  1. 2023Closed-loop Analysis of Vision-based Autonomous Systems: A Case Studycited by 18
  2. 2025Scenario-based Compositional Verification of Autonomous Systems with Neural Perceptioncited by 2
  3. 2023Is Certifying ℓp Robustness Still Worthwhile?cited by 1
  4. 2023Refining Perception Contracts: Case Studies in Vision-based Safe Auto-landingcited by 1
  5. 2026Mind the Prompt: Self-adaptive Generation of Task Plan Explanations via LLMscited by 1