Neural Control and Certificate Repair via Runtime Monitoring
- URL: http://arxiv.org/abs/2412.12996v1
- Date: Tue, 17 Dec 2024 15:15:30 GMT
- Title: Neural Control and Certificate Repair via Runtime Monitoring
- Authors: Emily Yu, Đorđe Žikelić, Thomas A. Henzinger,
- Abstract summary: We propose a novel framework that utilizes runtime monitoring to detect system behaviors that violate the property of interest.
We demonstrate the effectiveness of our approach by using it to repair and to boost the safety rate of neural network policies learned.
- Score: 7.146556437126553
- License:
- Abstract: Learning-based methods provide a promising approach to solving highly non-linear control tasks that are often challenging for classical control methods. To ensure the satisfaction of a safety property, learning-based methods jointly learn a control policy together with a certificate function for the property. Popular examples include barrier functions for safety and Lyapunov functions for asymptotic stability. While there has been significant progress on learning-based control with certificate functions in the white-box setting, where the correctness of the certificate function can be formally verified, there has been little work on ensuring their reliability in the black-box setting where the system dynamics are unknown. In this work, we consider the problems of certifying and repairing neural network control policies and certificate functions in the black-box setting. We propose a novel framework that utilizes runtime monitoring to detect system behaviors that violate the property of interest under some initially trained neural network policy and certificate. These violating behaviors are used to extract new training data, that is used to re-train the neural network policy and the certificate function and to ultimately repair them. We demonstrate the effectiveness of our approach empirically by using it to repair and to boost the safety rate of neural network policies learned by a state-of-the-art method for learning-based control on two autonomous system control tasks.
Related papers
- Transfer of Safety Controllers Through Learning Deep Inverse Dynamics Model [4.7962647777554634]
Control barrier certificates have proven effective in formally guaranteeing the safety of the control systems.
Design of a control barrier certificate is a time-consuming and computationally expensive endeavor.
We propose a validity condition that, when met, guarantees correctness of the controller.
arXiv Detail & Related papers (2024-05-22T15:28:43Z) - Value Functions are Control Barrier Functions: Verification of Safe
Policies using Control Theory [46.85103495283037]
We propose a new approach to apply verification methods from control theory to learned value functions.
We formalize original theorems that establish links between value functions and control barrier functions.
Our work marks a significant step towards a formal framework for the general, scalable, and verifiable design of RL-based control systems.
arXiv Detail & Related papers (2023-06-06T21:41:31Z) - In-Distribution Barrier Functions: Self-Supervised Policy Filters that
Avoid Out-of-Distribution States [84.24300005271185]
We propose a control filter that wraps any reference policy and effectively encourages the system to stay in-distribution with respect to offline-collected safe demonstrations.
Our method is effective for two different visuomotor control tasks in simulation environments, including both top-down and egocentric view settings.
arXiv Detail & Related papers (2023-01-27T22:28:19Z) - Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions [60.26921219698514]
We introduce a model-uncertainty-aware reformulation of CBF-based safety-critical controllers.
We then present the pointwise feasibility conditions of the resulting safety controller.
We use these conditions to devise an event-triggered online data collection strategy.
arXiv Detail & Related papers (2022-08-23T05:02:09Z) - Learning Stabilizing Policies in Stochastic Control Systems [20.045860624444494]
We study the effectiveness of jointly learning a policy together with a martingale certificate that proves its stability using a single learning algorithm.
Our results suggest that some form of pre-training of the policy is required for the joint optimization to repair and verify the policy successfully.
arXiv Detail & Related papers (2022-05-24T11:38:22Z) - Joint Differentiable Optimization and Verification for Certified
Reinforcement Learning [91.93635157885055]
In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties.
We propose a framework that jointly conducts reinforcement learning and formal verification.
arXiv Detail & Related papers (2022-01-28T16:53:56Z) - Safe RAN control: A Symbolic Reinforcement Learning Approach [62.997667081978825]
We present a Symbolic Reinforcement Learning (SRL) based architecture for safety control of Radio Access Network (RAN) applications.
We provide a purely automated procedure in which a user can specify high-level logical safety specifications for a given cellular network topology.
We introduce a user interface (UI) developed to help a user set intent specifications to the system, and inspect the difference in agent proposed actions.
arXiv Detail & Related papers (2021-06-03T16:45:40Z) - Closing the Closed-Loop Distribution Shift in Safe Imitation Learning [80.05727171757454]
We treat safe optimization-based control strategies as experts in an imitation learning problem.
We train a learned policy that can be cheaply evaluated at run-time and that provably satisfies the same safety guarantees as the expert.
arXiv Detail & Related papers (2021-02-18T05:11:41Z) - Runtime-Safety-Guided Policy Repair [13.038017178545728]
We study the problem of policy repair for learning-based control policies in safety-critical settings.
We propose to reduce or even eliminate control switching by repairing' the trained policy based on runtime data produced by the safety controller.
arXiv Detail & Related papers (2020-08-17T23:31:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.