Nannan Rong

This paper investigates the path-following control of autonomous vehicle by proposing a dual-controllers deep deterministic policy gradient. Dual-controllers match with the lateral and longitudinal control of vehicle, respectively. The main contributions are threefold: (1) We consider six lateral and three longitudinal state variates separately, aiming to reduce lateral and longitudinal coupling. (2) A dual-controllers is designed correspondingly to control lateral steering angle and longitudinal acceleration. It utilizes a shared experience replay pool to achieve efficient training. (3) A novel dual-stage reward mechanism is designed for the two controllers, which combines direct error feedback and indirect incremental guidance to balance lateral tracking accuracy and longitudinal safety coordination. This design yields better training performance compared to a simple reward function. Finally, MATLAB is employed for experimental verification, while CarSim simulations are utilized for physical validation. The simulation results show that it outperforms other methods.

This paper analyzes the adaptive synchronization of heterogeneous multi-layer networks. The intermittent adaptive laws are designed for intra- and inter-layer coupling weights, under which the intra-layer synchronization and inter-layer quasi-synchronization are achieved, respectively. Some concise synchronization criteria are formulated by constructing piecewise Lyapunov functions. The criteria are dependent on the local topology information but are independent of the update and stop time intervals. An estimation method is also presented to calculate the inter-layer error convergence region. Additionally, the proposed method is applied to homogeneous multi-layer networks, and it yields complete synchronization for both intra- and inter-layer networks. Finally, simulations on the Lorenz system and the UGV–UAV system are conducted to verify the effectiveness of the proposed intermittent adaptive synchronization method.

Cyberattacks significantly compromise the security of sensor networks, which largely hinder the accuracy and privacy of the information interaction process. However, it is tough to identify the attacks with unknown statistical models by a traditional detection scheme. This article is concerned with the resilient set-membership estimation for 2-D systems over sensor networks subject to cyberattacks and unknown-but-bounded noises. First, using the dynamic watermarking (DW) technique, a novel attack detection method is proposed to guarantee the security of information transmission among sensors. Compared to existing results on attack detection, the developed mechanism is capable of adapting to the ellipsoid-dependent set-membership estimation framework that incorporates the set ideas. Second, a group of scalable resilient set-membership estimators are derived for large-scale sensor networks. Each sensor has access to an ellipsoidal estimation set containing the true state of the system, in which the proposed design procedure is independent of global information about the network topology. Third, a set of parameter optimization algorithms is introduced in a recursive manner, which allows the sensor network to obtain a satisfactory estimation performance utilizing the designed estimation gain and detection mechanism. Lastly, a simulation example is shown to evaluate the availability and superiority of the proposed technique.

The intelligent and connected vehicle platoon control system requires supercomputing capabilities and scalability to process and store data for complex tasks in face of increasingly complex information. Traditional platoon control platforms are inadequate to handle enormous computational requirements. In this paper, we propose a cloud predictive control (CPC) architecture to achieve cooperative control in vehicle platoon system. Firstly, the CPC architecture provides remote control, effective monitoring, and platoon data collection through cloud technology and vehicle communications. This integration enhances the coordination and operation of platoon by centralizing control and information flow. Secondly, due to the hard constraints for vehicles in actual platoon system, this paper introduces a cloud predictive method for designing controller. Additionally, since a large amount of data needs to be processed by the cloud, quantization techniques are utilized to reduce the transmission cost. The stability of individual vehicle and overall stability of platoon are analyzed in this paper. Finally, the proposed method is validated through simulation experiments.

In this paper, event-triggered control synthesis of Interval Type-2 Takagi-Sugeno (IT2 T-S) fuzzy interconnected system is investigated via aperiodic intermittent method. Remarkably, time scale differential equation is introduced to construct a hybrid mode of discrete and continuous interconnections. An aperiodic intermittent control mindset is proposed inspired by the system energy attenuation characteristics. What’s more, a novel event-triggered mechanism embedding exponential decay function is developed to help reduce the sampling amount during the work cycle. By establishing time-scale type Lyapunov functions, sufficient criterion is obtained to guarantee stabilization of IT2 T-S fuzzy interconnected system with no Zeno behavior. Finally, some simulations on different time scales are given to verify the effectiveness of the proposed method.