Banglong Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Banglong Liu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Zhengfeng Yang
East China Normal University, Shanghai, Shanghai, China
3 shared publications - Hanrui Zhao
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China
2 shared publications - Xia Zeng
Southwest University
2 shared publications - Zhenbing Zeng
Shandong Xiehe University, Jinan, Shandong, China
2 shared publications Haifeng Qian
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China
1 shared publication- Huijiao Xie
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China
1 shared publication
Latest Publications
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45 (5) , 2460-2473
Safe Reinforcement Learning for NN-Controlled Systems With Neural Barrier Certificate Guidance
Safe controller synthesis is crucial for safety-critical applications. This article presents a novel reinforcement learning (RL) approach to synthesize safe controllers for neural network (NN)-controlled systems. The core idea leverages an iterative scheme that combines controller learning with neural barrier certificate (BC) verification, ultimately producing a provably safe deep neural network (DNN) controller with formal safety guarantees. The process begins by pretraining a well-performing DNN controller as an “oracle” via deep RL (DRL). To formally verify the safety properties of the closed-loop system under the base controller, we devise a formal verification procedure that approximates the DNN controller using polynomial inclusion, followed by synthesizing neural BCs via sum-of-squares (SOS) relaxation. In cases where the base controller is insufficient to yield a real BC, the current spurious BC is incorporated as an additional penalty term to reshape the RL reward function, guiding the iterative refinement for new controllers. We implement an automated tool, neural BC-guided safe RL NBCRL, and experimental results demonstrate the benefits of our method in terms of efficiency and scalability even for a nonlinear system with a dimension up to 12.
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45 (5) , 2460-2473
Safe Reinforcement Learning for NN-Controlled Systems With Neural Barrier Certificate Guidance
Safe controller synthesis is crucial for safety-critical applications. This article presents a novel reinforcement learning (RL) approach to synthesize safe controllers for neural network (NN)-controlled systems. The core idea leverages an iterative scheme that combines controller learning with neural barrier certificate (BC) verification, ultimately producing a provably safe deep neural network (DNN) controller with formal safety guarantees. The process begins by pretraining a well-performing DNN controller as an “oracle” via deep RL (DRL). To formally verify the safety properties of the closed-loop system under the base controller, we devise a formal verification procedure that approximates the DNN controller using polynomial inclusion, followed by synthesizing neural BCs via sum-of-squares (SOS) relaxation. In cases where the base controller is insufficient to yield a real BC, the current spurious BC is incorporated as an additional penalty term to reshape the RL reward function, guiding the iterative refinement for new controllers. We implement an automated tool, neural BC-guided safe RL NBCRL, and experimental results demonstrate the benefits of our method in terms of efficiency and scalability even for a nonlinear system with a dimension up to 12.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (11) , 3756-3767
Polynomial Neural Barrier Certificate Synthesis of Hybrid Systems via Counterexample Guidance
This article presents a novel approach to the safety verification of hybrid systems by synthesizing neural barrier certificates (BCs) via counterexample-guided neural network (NN) learning combined with sum-of-square (SOS)-based verification. We learn more easily verifiable BCs with NN polynomial expansions in a high-accuracy counterexamples guided framework. By leveraging the polynomial candidates yielded from the learning phase, we reformulate the identification of real BCs as convex linear matrix inequality (LMI) feasibility testing problems, instead of directly solving the inherently NP-hard nonconvex bilinear matrix inequality (BMI) problems associated with SOS-based BC generation. Furthermore, we decompose the large SOS verification programming into several manageable subprogrammings. Benefiting from the efficiency and scalability advantages, our approach can synthesize BCs not amenable to existing methods and handle more general hybrid systems.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (11) , 3756-3767
Polynomial Neural Barrier Certificate Synthesis of Hybrid Systems via Counterexample Guidance
This article presents a novel approach to the safety verification of hybrid systems by synthesizing neural barrier certificates (BCs) via counterexample-guided neural network (NN) learning combined with sum-of-square (SOS)-based verification. We learn more easily verifiable BCs with NN polynomial expansions in a high-accuracy counterexamples guided framework. By leveraging the polynomial candidates yielded from the learning phase, we reformulate the identification of real BCs as convex linear matrix inequality (LMI) feasibility testing problems, instead of directly solving the inherently NP-hard nonconvex bilinear matrix inequality (BMI) problems associated with SOS-based BC generation. Furthermore, we decompose the large SOS verification programming into several manageable subprogrammings. Benefiting from the efficiency and scalability advantages, our approach can synthesize BCs not amenable to existing methods and handle more general hybrid systems.
- Open Access
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Safe Controller Synthesis for Nonlinear Systems via Reinforcement Learning and PAC Approximation
Controller synthesis for nonlinear systems is an important research issue. Deep Neural Network (DNN) control policies obtained through reinforcement learning (RL), though exhibiting good performance in simulations, cannot be applied to safety-critical systems for lack of formal guarantee. To address this, this paper considers fully utilizing the advantages of RL for complex control tasks to obtain a well-performing DNN controller. Then, using PAC (Probably Approximately Correct) techniques, a polynomial surrogate controller with probabilistically controllable approximation error is obtained. Finally, the safety of the control system under the designed polynomial controller is verified using barrier certificate generation. Experiments demonstrate the effectiveness of our method in generating controllers with safety guarantees for systems with high dimensions and degrees.
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessSafe Controller Synthesis for Nonlinear Systems via Reinforcement Learning and PAC Approximation
Controller synthesis for nonlinear systems is an important research issue. Deep Neural Network (DNN) control policies obtained through reinforcement learning (RL), though exhibiting good performance in simulations, cannot be applied to safety-critical systems for lack of formal guarantee. To address this, this paper considers fully utilizing the advantages of RL for complex control tasks to obtain a well-performing DNN controller. Then, using PAC (Probably Approximately Correct) techniques, a polynomial surrogate controller with probabilistically controllable approximation error is obtained. Finally, the safety of the control system under the designed polynomial controller is verified using barrier certificate generation. Experiments demonstrate the effectiveness of our method in generating controllers with safety guarantees for systems with high dimensions and degrees.