# Neural Simplex Architecture

arXiv: https://arxiv.org/abs/1908.00528 · HTML: https://mlsanity.com/paper/1908.00528/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2019.

## Built on by (most cited first, 29 of 29)

- [Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes](https://mlsanity.com/paper/2210.10691/) (2022)
- [Conformal Quantitative Predictive Monitoring of STL Requirements for Stochastic Processes](https://mlsanity.com/paper/2211.02375/) (2022)
- [Runtime Safety Assurance for Learning-enabled Control of Autonomous Driving Vehicles](https://mlsanity.com/paper/2109.13446/) (2021)
- [Neural Predictive Monitoring under Partial Observability](https://mlsanity.com/paper/2108.07134/) (2021)
- [Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents](https://mlsanity.com/paper/2207.04117/) (2022)
- [Probabilistic Reach-Avoid for Bayesian Neural Networks](https://mlsanity.com/paper/2310.01951/) (2023)
- [Causal Scene Narration with Runtime Safety Supervision for Vision-Language-Action Driving](https://mlsanity.com/paper/2604.01723/) (2026)
- [Dynamic Simplex: Balancing Safety and Performance in Autonomous Cyber Physical Systems](https://mlsanity.com/paper/2302.09750/) (2023)
- [Language-Enhanced Latent Representations for Out-of-Distribution Detection in Autonomous Driving](https://mlsanity.com/paper/2405.01691/) (2024)
- [Sovereign Assurance Boundary: Certificate-Bound Admission for Agentic Infrastructure](https://mlsanity.com/paper/2606.11632/) (2026)
- [Safety Monitoring of Machine Learning Perception Functions: a Survey](https://mlsanity.com/paper/2412.06869/) (2024)
- [Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer](https://mlsanity.com/paper/2606.09416/) (2026)
- [The Use of the Simplex Architecture to Enhance Safety in Deep-Learning-Powered Autonomous Systems](https://mlsanity.com/paper/2509.21014/) (2025)
- [Shields to Guarantee Probabilistic Safety in MDPs](https://mlsanity.com/paper/2605.10888/) (2026)
- [Semantic Quorum Assurance: Collective Certification for Non-Deterministic AI Infrastructure](https://mlsanity.com/paper/2606.08021/) (2026)
- [Perception Simplex: Verifiable Collision Avoidance in Autonomous Vehicles Amidst Obstacle Detection Faults](https://mlsanity.com/paper/2209.01710/) (2022)
- [Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning](https://mlsanity.com/paper/2305.14872/) (2023)
- [A Barrier Certificate-based Simplex Architecture for Systems with Approximate and Hybrid Dynamics](https://mlsanity.com/paper/2202.09710/) (2022)
- [An Empirical Analysis of the Use of Real-Time Reachability for the Safety Assurance of Autonomous Vehicles](https://mlsanity.com/paper/2205.01419/) (2022)
- [Safe Policy Improvement in Constrained Markov Decision Processes](https://mlsanity.com/paper/2210.11259/) (2022)
- [Real-DRL: Teach and Learn in Reality](https://mlsanity.com/paper/2511.00112/) (2025)
- [Reversible Simplex Supervision with Post-Action Debt Accounting for Goal-Reaching RL](https://mlsanity.com/paper/2601.19499/) (2026)
- [Synergistic Simplex: Cooperative Runtime Assurance for Safety-Critical Autonomous Systems](https://mlsanity.com/paper/2605.08190/) (2026)
- [Reliability-Asymmetric Spacecraft Autonomy: Co-Designing a Capable Learned GNC Stack with a Verified, Adaptation-Aware Runtime Shield](https://mlsanity.com/paper/2606.25366/) (2026)
- [Conformal Recovery-Deadline Certificates for Runtime Assurance of Adapting Controllers](https://mlsanity.com/paper/2606.25371/) (2026)
- [Safe Online Learning via Smooth Safety-Structured Policy Composition](https://mlsanity.com/paper/2606.31320/) (2026)
- [Cognitively-Grounded On-Device Runtime Learning for Ground Robots in Unknown Physical Environments](https://mlsanity.com/paper/2608.28677/) (2026)
- [Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models](https://mlsanity.com/paper/2609.22243/) (2026)
- [Requirement-Bound Verified Commissioning: A Frozen Four-Billion-Parameter Local Model as a Candidate Generator under an External Acceptance Layer with Verification and Release Authority](https://mlsanity.com/paper/2609.30219/) (2026)

## Abstract (arXiv)

We present the Neural Simplex Architecture (NSA), a new approach to runtime assurance that provides safety guarantees for neural controllers (obtained e.g. using reinforcement learning) of autonomous and other complex systems without unduly sacrificing performance. NSA is inspired by the Simplex control architecture of Sha et al., but with some significant differences. In the traditional approach, the advanced controller (AC) is treated as a black box; when the decision module switches control to the baseline controller (BC), the BC remains in control forever. There is relatively little work on switching control back to the AC, and there are no techniques for correcting the AC's behavior after it generates a potentially unsafe control input that causes a failover to the BC. Our NSA addresses both of these limitations. NSA not only provides safety assurances in the presence of a possibly unsafe neural controller, but can also improve the safety of such a controller in an online setting via retraining, without overly degrading its performance. To demonstrate NSA's benefits, we have conducted several significant case studies in the continuous control domain. These include a target-seeking ground rover navigating an obstacle field, and a neural controller for an artificial pancreas system.