Learning-enabled controllers with stability certificate functions have demonstrated impressive empirical performance in addressing control problems in recent years. Nevertheless, directly deploying the neural controllers onto actual digital platforms requires impractically excessive communication resources due to a continuously updating demand from the closed-loop feedback controller. We introduce a framework aimed at learning the event-triggered controller (ETC) with optimal scheduling, i.e., minimal triggering times, to address this challenge in resource-constrained scenarios. Our proposed framework, denoted by Neural ETC, includes two practical algorithms: the path integral algorithm based on directly simulating the event-triggered dynamics, and the Monte Carlo algorithm derived from new theoretical results regarding lower bound of inter-event time. Furthermore, we propose a projection operation with an analytical expression that ensures theoretical stability and schedule optimality for Neural ETC. 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.

In order to stabilize nonlinear systems modeled by stochastic differential equations, we design a Fast Exponentially Stable and Safe Neural Controller (FESSNC) for fast learning controllers. Our framework is parameterized by neural networks, and realizing both rigorous exponential stability and safety guarantees. Concretely, we design heuristic methods to learn the exponentially stable and the safe controllers, respectively, in light of the classical theory of stochastic exponential stability and our established theorem on guaranteeing the almost-sure safety for stochastic dynamics. More significantly, to rigorously ensure the stability and the safety guarantees for the learned controllers, we develop a projection operator, projecting to the space of exponentially-stable and safe controllers. To reduce the highly computational cost for solving the projection operation, approximate projection operators are delicately proposed with closed forms that map the learned controllers to the target controller space. Furthermore, we employ Hutchinson's trace estimator for a scalable unbiased estimate of the Hessian matrix that is used in the projection operator, which thus allows for reducing computational cost and, therefore, can accelerate the training and testing processes. More importantly, our approximate projection operations are applicable to the nonparametric control methods, improving their stability and safety performance. We empirically demonstrate the superiority of the FESSNC over the existing methods.

Crowdsensing is a system which collects sensing data through recruiting a large number of participants to perform the sensing tasks. It consists of two parts: 1) the platform side and 2) the user side. The incentive mechanism is necessary to recruit a sufficient number of participants for the utility of the platform, and to guarantee the utility of the participants for the users. Current mechanisms for crowdsensing are based on traditional economics with two basic hypotheses. The first is that the preference of people is constant, which implies that their preference for an item does not change under different circumstances; the second is that the utility of people is equal to the payment they obtain. However, decoy effect from behavioral economics shows that people's preferences change as the alternative set changes. And resulting from fairness preference theory, people's utility depends not only on the actual income they receive but also on the fairness of the income of all people. Thus, current incentive mechanisms will lead to users' wrong selection making. To solve these problems, we design the framework for publishing tasks based on decoy effect (FPDE) mechanism on the platform side. And we design the payoff allocation based on fairness preference (PAFP) mechanism for the user side. We compare our mechanisms with a new and advanced mechanism called incentive mechanism for crowdsensing-centric (IMCC) model. The simulations show that FPDE can increase the utility of the platform by approximately 20.8%, and the utility of the users will increases by 14.8% under PAFP.