Neural Event-Triggered Control with Optimal Scheduling
Authors: Luan Yang, Jingdong Zhang, Qunxi Zhu, Wei Lin
ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Compared to the conventional neural controllers, our empirical results show that the Neural ETC significantly reduces the required communication resources while enhancing the control performance in constrained communication resources scenarios. Finally, we evaluate Neural ETCs on a variety of representative physical and engineering systems. |
| Researcher Affiliation | Academia | 1Research Institute of Intelligent Complex Systems, Fudan University, China. 2School of Mathematical Sciences, LMNS, and SCMS, Fudan University, China. 3State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science, Institutes of Brain Science, Fudan University, China. 4Shanghai Artificial Intelligence Laboratory, China. Correspondence to: Qunxi Zhu <EMAIL>, Wei Lin <EMAIL>. |
| Pseudocode | Yes | The whole training procedure is summarized in Algorithm 1. The specific training procedure of this algorithm, dubbed Neural ETC-MC, is shown in Algorithm 2. |
| Open Source Code | Yes | The code for reproducing all the numerical experiments is released at https://github.com/jingddong-zhang/Neural Event-triggered-Control (hyperlink of Neural ETC). |
| Open Datasets | No | For training controller u, we uniformly sample 1000 data from the state region [ -10, 10]. |
| Dataset Splits | No | For training controller u, we uniformly sample 1000 data from the state region [ -10, 10]. |
| Hardware Specification | Yes | We implement the code on a single i7-10870 CPU with 16GB memory, and we train all the parameters with Adam optimizer. |
| Software Dependencies | No | We implement the code on a single i7-10870 CPU with 16GB memory, and we train all the parameters with Adam optimizer. We solve this problem with the QP solver in cvxopt in Python package. The lqr method in Matlab. |
| Experiment Setup | Yes | We set the iterations for warm up as 500, the iterations and batch size for calculating the triggering times as 50 and 10, the learning rate as lr = 0.01, the weight factor for event loss as λ2 = 10 1000. For implementing the controller in the event-triggered mode, we set the event function... where the σ is set as 0.5 for all models. |