Enforcing hard constraints with soft barriers: Safe reinforcement learning in unknown stochastic environments

Y Wang, SS Zhan, R Jiao, Z Wang… - International …, 2023 - proceedings.mlr.press
It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an
unknown and stochastic environment under hard constraints that require the system state …

Efficient global robustness certification of neural networks via interleaving twin-network encoding

Z Wang, C Huang, Q Zhu - 2022 Design, Automation & Test in …, 2022 - ieeexplore.ieee.org
The robustness of deep neural networks has received significant interest recently, especially
when being deployed in safety-critical systems, as it is important to analyze how sensitive …

Physics-aware safety-assured design of hierarchical neural network based planner

X Liu, C Huang, Y Wang, B Zheng… - 2022 ACM/IEEE 13th …, 2022 - ieeexplore.ieee.org
Neural networks have shown great promises in planning, control, and general decision
making for learning-enabled cyber-physical systems (LE-CPSs), especially in improving …

Joint differentiable optimization and verification for certified reinforcement learning

Y Wang, S Zhan, Z Wang, C Huang, Z Wang… - Proceedings of the …, 2023 - dl.acm.org
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 …

Design-while-verify: correct-by-construction control learning with verification in the loop

Y Wang, C Huang, Z Wang, Z Wang… - Proceedings of the 59th …, 2022 - dl.acm.org
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 …

Cross-layer adaptation with safety-assured proactive task job skipping

Z Wang, C Huang, H Kim, W Li, Q Zhu - ACM Transactions on Embedded …, 2021 - dl.acm.org
During the operation of many real-time safety-critical systems, there are often strong needs
for adapting to a dynamic environment or evolving mission objectives, eg, increasing …

Cloud and Edge Computing for Connected and Automated Vehicles

Q Zhu, B Yu, Z Wang, J Tang, QA Chen… - … and Trends® in …, 2023 - nowpublishers.com
The recent development of cloud computing and edge computing shows great promise for
the Connected and Automated Vehicle (CAV), by enabling CAVs to offload their massive on …

Online Adaptive Neural Observer for Prescribed Performance Hyper-Chaotic Systems

HPH Anh, NT Dat - Knowledge-Based Systems, 2024 - Elsevier
This paper proposes a new neural-based algorithm applied to online identifying, observing,
and adaptively controlling of uncertain nonlinear systems via which the system transient and …

Verification in the loop: Correct-by-construction control learning with reach-avoid guarantees

Y Wang, C Huang, Z Wang, Z Wang, Q Zhu - arXiv preprint arXiv …, 2021 - arxiv.org
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 …

Verification and Design of Robust and Safe Neural Network-enabled Autonomous Systems

Q Zhu, W Li, C Huang, X Chen, W Zhou… - 2023 59th Annual …, 2023 - ieeexplore.ieee.org
Neural networks are being applied to a wide range of tasks in autonomous systems, such as
perception, prediction, planning, control, and general decision making. While they may …