Verification in the loop: Correct-by-construction control learning with reach-avoid guarantees
In the current control design of safety-critical autonomous systems, formal verification
techniques are typically applied after the controller is designed to evaluate whether the …
techniques are typically applied after the controller is designed to evaluate whether the …
Design-while-verify: correct-by-construction control learning with verification in the loop
In the current control design of safety-critical cyber-physical systems, formal verification
techniques are typically applied after the controller is designed to evaluate whether the …
techniques are typically applied after the controller is designed to evaluate whether the …
Scalable synthesis of verified controllers in deep reinforcement learning
Z Xiong, S Jagannathan - arXiv preprint arXiv:2104.10219, 2021 - arxiv.org
There has been significant recent interest in devising verification techniques for learning-
enabled controllers (LECs) that manage safety-critical systems. Given the opacity and lack of …
enabled controllers (LECs) that manage safety-critical systems. Given the opacity and lack of …
Joint differentiable optimization and verification for certified reinforcement learning
Model-based reinforcement learning has been widely studied for controller synthesis in
cyber-physical systems (CPSs). In particular, for safety-critical CPSs, it is important to …
cyber-physical systems (CPSs). In particular, for safety-critical CPSs, it is important to …
Safety and liveness guarantees through reach-avoid reinforcement learning
Reach-avoid optimal control problems, in which the system must reach certain goal
conditions while staying clear of unacceptable failure modes, are central to safety and …
conditions while staying clear of unacceptable failure modes, are central to safety and …
Safe reinforcement learning via formal methods: Toward safe control through proof and learning
Formal verification provides a high degree of confidence in safe system operation, but only if
reality matches the verified model. Although a good model will be accurate most of the time …
reality matches the verified model. Although a good model will be accurate most of the time …
Safety aware model-based reinforcement learning for optimal control of a class of output-feedback nonlinear systems
The ability to learn and execute optimal control policies safely is critical to realization of
complex autonomy, especially where task restarts are not available and/or the systems are …
complex autonomy, especially where task restarts are not available and/or the systems are …
Verified Safe Reinforcement Learning for Neural Network Dynamic Models
J Wu, H Zhang, Y Vorobeychik - arXiv preprint arXiv:2405.15994, 2024 - arxiv.org
Learning reliably safe autonomous control is one of the core problems in trustworthy
autonomy. However, training a controller that can be formally verified to be safe remains a …
autonomy. However, training a controller that can be formally verified to be safe remains a …
Transfer of Safety Controllers Through Learning Deep Inverse Dynamics Model
Control barrier certificates have proven effective in formally guaranteeing the safety of the
control systems. However, designing a control barrier certificate is a time-consuming and …
control systems. However, designing a control barrier certificate is a time-consuming and …
Model-free learning for safety-critical control systems: A reference governor approach
This paper describes a learning-based approach to operating safety-critical control systems.
A reference governor is an add-on scheme used to guard the nominal system against …
A reference governor is an add-on scheme used to guard the nominal system against …