Noncooperative Game-Based Cooperative Maneuvering of Intelligent Surface Vehicles via Accelerated Learning-Based Neural Predictors

IEEE Transactions on Intelligent Vehicles, Год журнала: 2022, Номер 8(3), С. 2212 - 2221

Опубликована: Ноя. 14, 2022

This paper investigates a noncooperative game-based cooperative maneuvering problem of multiple intelligent surface vehicles (ISVs) subject to uncertain nonlinearities and external disturbances. There exists conflict between the overall objective swarm own parameterized individual tasks each ISV, resulting in game. A distributed control method is proposed for ISVs. Specifically, at first, action estimators are designed ISV based on information neighboring ISVs estimate actions other Then, an accelerated learning-based neural predictor designed, where echo state network introduced as identifier nonlinearities, adaptation laws developed high-order tuner accelerate convergence rate. Finally, controllers update variables Nash equilibrium seeking approach, time derivative kinematic law obtained nonlinear command filter. The architecture modular, leading decoupling estimator module, controller module. Using cascade system theory, input-to-state stability closed-loop guaranteed three subsystems. simulation example provided validate effectiveness method.

Язык: Английский

---

Output-Feedback Finite-Time Safety-Critical Coordinated Control of Path-Guided Marine Surface Vehicles Based on Neurodynamic Optimization

IEEE Transactions on Systems Man and Cybernetics Systems, Год журнала: 2022, Номер 53(3), С. 1788 - 1800

Опубликована: Сен. 22, 2022

In the presence of static and moving obstacles, this article investigates an output-feedback finite-time safety-critical coordinated control method multiple under-actuated marine surface vehicles (MSVs) subject to velocity input constraints. Specifically, based on robust exact differentiators, a state observer (FTSO) is first developed recover unavailable velocities while estimating total disturbances containing model uncertainties environmental disturbances. Next, with aid estimated from FTSO, nominal guidance law designed for achieving distributed formation MSVs at kinematic level. By forward invariance principle, barrier functions (FTCBFs) are used construct collision-free sets multi-MSV system. To unify safety objectives, quadratic optimization problems formulated under facilitate real-time implementations, one-layer recurrent neural networks employed solve problem. Then, FTSO presented kinetic The optimal laws solved within All error signals closed-loop system proved be uniformly ultimately bounded, ensured safe. Simulation results provided demonstrate effectiveness superiority proposed FTCBF-based method.

Язык: Английский

---

Composite Anti-Disturbance Dynamic Positioning for Mass-Switched Unmanned Marine Vehicles

IEEE Transactions on Intelligent Vehicles, Год журнала: 2023, Номер 9(1), С. 1890 - 1898

Опубликована: Май 23, 2023

This article presents a composite anti-disturbance dynamic positioning (CADDP) control technique for mass-switched unmanned marine vehicle (MSUMV) subject to the influence of wave drifts and residual filtered wave. The are described as unmeasurable modeled disturbances measurable unmodeled disturbances, respectively. Then, UMV with mass switching is switched system. Further, by virtue multiple Lyapunov functions technique, DP achieved disturbance rejection capability. effectiveness presented method illustrated simulations supply vessel.

Язык: Английский

---

Safety-Critical Trajectory Tracking for Mobile Robots with Guaranteed Performance

IEEE/CAA Journal of Automatica Sinica, Год журнала: 2024, Номер 11(9), С. 2033 - 2035

Опубликована: Июнь 6, 2024

Dear Editor, This letter considers a collision-free trajectory tracking problem for performance-guaranteed mobile robots (MRs) subject to obstacles. We propose safety-critical method based on control barrier functions (CBFs). First, an auxiliary system is established generate the non-negative signals inflexible bounds such that performance constraints are not violated when avoiding Next, desired guidance laws devised evolve errors within space by error transformation technique. Then, position-heading CBF heading principle developed. Under framework, angle speed law solved quadratic program with respect constraints. It proved all can converge and prescribed space, closed-loop ensured be safe. Finally, simulation experiment results given verify effectiveness feasibility of proposed scheme.

Язык: Английский

---

Safe Control Against Uncertainty: A Comprehensive Review of Control Barrier Function Strategies

IEEE Systems Man and Cybernetics Magazine, Год журнала: 2025, Номер 11(1), С. 34 - 47

Опубликована: Янв. 1, 2025

The growing interest in robust designs and data-driven technologies for safe control problems underscores the critical need to understand uncertainty ensuring reliable safety guarantees. This review offers a concise survey of recent advancements barrier function (CBF) method, widely recognized as principled effective approach control, particularly context uncertainty. From unified perspective, we classify into three types based on their learnability transferability. Then explore techniques associated with each type found existing literature. Additionally, highlight knowledge-based framework that utilizes meta-learning address dynamic uncertainty, shedding light potential future investigations practical learning algorithms problems. Furthermore, employ topic modeling identify generalize topics from literature, thus revealing research trends ongoing real-world applications withing scope control.

Язык: Английский

---

Parallel Path-Following Control of Fully-Actuated Autonomous Surface Vehicles Based on a High-Order Learning Extended State Observer

Lecture notes in electrical engineering, Год журнала: 2025, Номер unknown, С. 139 - 147

Опубликована: Янв. 1, 2025

Язык: Английский

---

A system for the validation of collision avoidance algorithm performance of autonomous ships

Ocean Engineering, Год журнала: 2023, Номер 280, С. 114600 - 114600

Опубликована: Май 4, 2023

Язык: Английский

---

Safety-Critical Parallel Trajectory Tracking Control of Maritime Autonomous Surface Ships Based on Integral Control Barrier Functions

IEEE Transactions on Intelligent Vehicles, Год журнала: 2024, Номер 9(5), С. 4979 - 4988

Опубликована: Фев. 2, 2024

This article investigates the parallel trajectory tracking control of fully-actuated maritime autonomous surface ships (MASSs) in presence multiple stationary/moving ocean obstacles. A safety-critical architecture is proposed for MASSs. Specifically, an artificial MASS system constructed based on a data-driven learning predictor where real-time and historical navigation data are both utilized to achieve estimation unknown weights Taylor polynomials Fourier series. Then, law designed such that capable track reference positively. Finally, integral barrier functions employed encode input safety constraints. optimization signal augmented collision avoidance all Based stability analyses, errors actual verified be uniformly ultimately bounded safe. Numerical examples confirm effectiveness scheme MASS.

Язык: Английский

---

Robust Target Interception Strategy for a USV With Experimental Validation

IEEE Robotics and Automation Letters, Год журнала: 2023, Номер 8(11), С. 7042 - 7049

Опубликована: Июль 31, 2023

This letter addresses the problem of designing an interception strategy for underactuated uncrewed surface vessel (USV) in presence uncertain external disturbances and unknown internal parameters i.e., linear nonlinear damping coefficients, vehicle mass, etc. The is developed based on backstepping technique, which guarantees that relative velocity between USV moving target can globally converge to desired value. Estimation laws are proposed estimate dynamic constant disturbances, improving robustness performance algorithm. A projection operator included estimation ensures estimates remain within a prescribed bound. stability analysis provided, both numerical simulation experimental results demonstrated validate efficiency strategy.

Язык: Английский

---

A Target Tracking Guidance for Unmanned Surface Vehicles in the Presence of Obstacles

IEEE Transactions on Intelligent Transportation Systems, Год журнала: 2023, Номер 25(5), С. 4102 - 4115

Опубликована: Ноя. 1, 2023

Dynamic target tracking technology has a broad application prospect in marine transportation, intelligent monitoring, border and coastal defense, etc. However, most guidance systems designed for unmanned surface vehicles (USVs) lack automatic obstacle avoidance capabilities, which limits their performance. To address this challenge, paper investigates USVs the presence of obstacles. In order to track target, sensors fixed on bow need be oriented toward especially when USV is sufficiently close target. For purpose, bias proportional navigation law with look angle constraints presented guiding follower orient approach moving navigate along safe route avoid obstacles, profile constraint formulated into by solving function final boundary conditions. The field experimentation takes place 40-meter-wide 80-meter-long section Huchuntang River. Here, equipped proposed effectively tracks while navigating around Results indicate that capable object, avoiding orienting at time. experimental test video (https://youtu.be/l5SQf2ZgcxM).

Язык: Английский

---