# MORTAR: A Model-based Runtime Action Repair Framework for AI-enabled Cyber-Physical Systems

arXiv: https://arxiv.org/abs/2408.03892 · HTML: https://mlsanity.com/paper/2408.03892/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 69 references that are in the map.
- First posted on arXiv 7 Aug 2024.

## Builds on (most cited first, 30 of 36)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [Recent Advances in Adversarial Training for Adversarial Robustness](https://mlsanity.com/paper/2102.01356/) (2021)
- [Generating Adversarial Examples with Adversarial Networks](https://mlsanity.com/paper/1801.02610/) (2018)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Safe Exploration in Continuous Action Spaces](https://mlsanity.com/paper/1801.08757/) (2018)
- [Projection-Based Constrained Policy Optimization](https://mlsanity.com/paper/2010.03152/) (2020)
- [A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems](https://mlsanity.com/paper/1705.01292/) (2017)
- [End-to-End Robotic Reinforcement Learning without Reward Engineering](https://mlsanity.com/paper/1904.07854/) (2019)
- [Conservative Safety Critics for Exploration](https://mlsanity.com/paper/2010.14497/) (2020)
- [LAS-AT: Adversarial Training with Learnable Attack Strategy](https://mlsanity.com/paper/2203.06616/) (2022)
- [Universal Adversarial Training](https://mlsanity.com/paper/1811.11304/) (2018)
- [Safe Reinforcement Learning Using Robust MPC](https://mlsanity.com/paper/1906.04005/) (2019)
- [Safe Reinforcement Learning with Model Uncertainty Estimates](https://mlsanity.com/paper/1810.08700/) (2018)
- [Neural Dynamic Policies for End-to-End Sensorimotor Learning](https://mlsanity.com/paper/2012.02788/) (2020)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions](https://mlsanity.com/paper/1901.10501/) (2019)
- [Shield Synthesis: Runtime Enforcement for Reactive Systems](https://mlsanity.com/paper/1501.02573/) (2015)
- [Deep Reinforcement Learning for Wireless Sensor Scheduling in Cyber-Physical Systems](https://mlsanity.com/paper/1809.05149/) (2018)
- [Comparison of Deep Reinforcement Learning and Model Predictive Control for Adaptive Cruise Control](https://mlsanity.com/paper/1910.12047/) (2019)
- [Neural Network Repair with Reachability Analysis](https://mlsanity.com/paper/2108.04214/) (2021)
- [Towards Building AI-CPS with NVIDIA Isaac Sim: An Industrial Benchmark and Case Study for Robotics Manipulation](https://mlsanity.com/paper/2308.00055/) (2023)

## Abstract (arXiv)

Cyber-Physical Systems (CPSs) are increasingly prevalent across various industrial and daily-life domains, with applications ranging from robotic operations to autonomous driving. With recent advancements in artificial intelligence (AI), learning-based components, especially AI controllers, have become essential in enhancing the functionality and efficiency of CPSs. However, the lack of interpretability in these AI controllers presents challenges to the safety and quality assurance of AI-enabled CPSs (AI-CPSs). Existing methods for improving the safety of AI controllers often involve neural network repair, which requires retraining with additional adversarial examples or access to detailed internal information of the neural network. Hence, these approaches have limited applicability for black-box policies, where only the inputs and outputs are accessible during operation. To overcome this, we propose MORTAR, a runtime action repair framework designed for AI-CPSs in this work. MORTAR begins by constructing a prediction model that forecasts the quality of actions proposed by the AI controller. If an unsafe action is detected, MORTAR then initiates a repair process to correct it. The generation of repaired actions is achieved through an optimization process guided by the safety estimates from the prediction model. We evaluate the effectiveness of MORTAR across various CPS tasks and AI controllers. The results demonstrate that MORTAR can efficiently improve task completion rates of AI controllers under specified safety specifications. Meanwhile, it also maintains minimal computational overhead, ensuring real-time operation of the AI-CPSs.