Event-triggered neural network control of autonomous surface vehicles over wireless network

Lv, Mingao; Wang, Dan; Peng, Zhouhua; Wang, Dan

doi:10.1007/s11432-019-2679-5

Cited by 13 publications

(6 citation statements)

References 38 publications

(111 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned above, the computation of ACR without considering the closed-loop effect leads to an oversimplified distribution model for the state estimation error and eventually returns approximated results. Assume that the open-loop state estimation error is subject to the dynamic model (3). Then, the error has a fully Gaussian PDF, and, similar to (21), the open-loop ACR can be recursively computed as (35) with Ȇ(δ 0 ) = 1, where P i , i = 1, 2, • • • , T, are the coefficients obtained by…”

Section: A Deviation Analysis Of the Conventional Methodsmentioning

confidence: 99%

“…The dynamic model (3) indicates that the estimation error accumulates over the time interval {ι + 1, ι + 2, • • • , k} due to the lack of state sampling. The error accumulation may lead to the degradation of the system control performance.…”

Section: Schedulermentioning

confidence: 99%

“…I N recent years, emerging networked control systems, such as intelligent industrial manufacturing [1], smart power grids [2], and autonomous vehicles [3], are characterized by a distributed design manner where the plants and the sensors are located remotely and are connected with a common network. The development of the closed-loop controllers for these systems requires sufficient sampling of the system states ensured by active communication of the network, such that the controllers always have access to the latest system states provided by the remote sensors through the network.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Average Communication Rate for Event-Triggered Stochastic Control Systems

Zhang¹,

Liu²,

Mamduhi³

et al. 2023

Preprint

View full text Add to dashboard Cite

Quantification of the triggering rates of an eventtriggered stochastic system with deterministic thresholds is a challenging problem due to the non-stationary nature of the system's stochastic processes. A typical example is the computation of the average communication rate (ACR) of the networked event-triggered stochastic control systems (ET-SCS) of which the communication of the sensor network is scheduled by whether a system variable of interest exceeds predefined constant thresholds. For such a system, a closed-loop effect emerges due to the interdependence between the system variable and the trigger of communication. This effect, commonly referred to as side information by related work, distorts the stochastic distribution of the system variables and makes the ACR computation non-trivial. Previous work in this area used to over-simplify the computation by ignoring the side information and misusing a Gaussian distribution, which leads to approximated results. This paper proposes both analytical and numerical approaches to predict the exact ACR for an ET-SCS using a recursive model. Furthermore, we use theoretical analysis and a numerical study to qualitatively evaluate the deviation gap of the conventional approach that ignores the side information. The accuracy of our proposed method, alongside its comparison with the simplified results of the conventional approach, is validated by experimental studies. Our work is promising to benefit the efficient resource planning of networked control systems with limited communication resources by providing accurate ACR computation.

show abstract

Section: A Deviation Analysis Of the Conventional Methodsmentioning

confidence: 99%

Section: Schedulermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Average Communication Rate for Event-Triggered Stochastic Control Systems

Zhang¹,

Liu²,

Mamduhi³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, event-triggered control of agent has attracted much attention, and event-triggered control has been gradually applied to multi-joint robots, 20 unmanned vehicles, 21 quadrotors, 22–24 and other agents. Although there have been some researches on the event-triggered control of USV, 25–28 but these researches are all about the control of fully actuated USV. The event-triggered control of underactuated USV has not been widely studied.…”

Section: Introductionmentioning

confidence: 99%

Event-triggered sliding mode trajectory tracking control for underactuated unmanned surface vessel

Zhao

Wang

2022

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

This article considers the trajectory tracking control for underactuated unmanned surface vessel and actuator loss caused by frequent updating of the controller. An event-triggered sliding mode trajectory tracking control algorithm is proposed for the problems. A sliding mode tracking controller is designed by the integral sliding surface at the beginning to guarantee global asymptotic tracking of the desired trajectory. Based on the tracking controller, the event-triggered condition is designed in the channel of the controller to actuator, which effectively reduces the update frequency of the controller. Theoretical analysis proves that the states of underactuated unmanned surface vessel are uniformly stable, while the Zeno behavior is prevented. The results of the numerical simulation are presented to demonstrate the effectiveness of the proposed algorithm.

show abstract

“…While a level of robustness against uncertainties and unmodeled dynamics can be expected, having the sensor continuously operating results in waste of resources. Related work can be found in [24]- [28]. Self-triggered control, on the other hand, determines the next sampling time and transmission once a sampled measurement is received, which does not need to continuously sample the outputs; see, e.g., [29]- [32].…”

mentioning

confidence: 99%

Data-driven Self-triggered Control via Trajectory Prediction

Liu¹,

Sun²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Self-triggered control, a well-documented technique for reducing the communication overhead while ensuring desired system performance, is gaining increasing popularity. However, existing methods for self-triggered control require explicit system models that are assumed perfectly known a priori. An end-to-end control paradigm known as data-driven control learns control laws directly from data, and offers a competing alternative to the routine system identification-then-control method. In this context, the present paper puts forth data-driven self-triggered control schemes for unknown linear systems using data collected offline. Specifically, for output feedback control systems, a datadriven model predictive control (MPC) scheme is proposed, which computes a sequence of control inputs while generating a predicted system trajectory. A data-driven self-triggering law is designed using the predicted trajectory, to determine the next triggering time once a new measurement becomes available. For state feedback control systems, instead of capitalizing on MPC to predict the trajectory, a data-fitting problem using the precollected input-state data is solved, whose solution is employed to construct the self-triggering mechanism. Both feasibility and stability are established for the proposed self-triggered controllers, which are validated using numerical examples.Index terms-Data-driven control, data-driven MPC, selftriggered control, predicted control. I. INTRODUCTIONThanks to recent advances in data acquisition and computing technologies, data-driven control has attracted considerable attention in the past years. Designing control laws directly from data without resorting to any system identification step, offers an appealing alternative to the traditional model-based control paradigm [1], [2]. This is because in real-world applications, it is always difficult or even impossible to acquire an accurate system model [3]- [5]. Indeed, a number of publications are devoted to studying data-driven control. These were mainly inspired by the celebrated Fundamental Lemma proposed in [6], which lays the theoretical foundation for data-driven control. Several control problems have been addressed under the new

show abstract

Event-triggered neural network control of autonomous surface vehicles over wireless network

Cited by 13 publications

References 38 publications

Average Communication Rate for Event-Triggered Stochastic Control Systems

Average Communication Rate for Event-Triggered Stochastic Control Systems

Event-triggered sliding mode trajectory tracking control for underactuated unmanned surface vessel

Data-driven Self-triggered Control via Trajectory Prediction

Contact Info

Product

Resources

About