Autonomous underwater vehicles (AUVs) have become important tools in the ocean exploration and drawn considerable attention. Precise control for AUVs is prerequisite to effectively execute tasks. However, classical methods such as model predictive (MPC) rely heavily on dynamics of controlled system which difficult obtain AUVs. To address this issue, a new reinforcement learning (RL) framework AUV path-following proposed article. Specifically, we propose novel actor-model-critic (AMC)...

This brief proposes a distributed predictive path following controller with arrival time awareness for multiple waterborne automated guided vessels (waterborne AGVs) applied to interterminal transport (ITT). The goal is design an efficient cooperative algorithm that solves local problems in parallel and minimizes overall objective. We model the ITT problem using AGVs independent dynamics objectives but coupling collision avoidance constraints. then solved by control (DMPC) of which...

Urban waterways have great potential in cargo transport to relieve the congestion overloaded road networks. This paper explores of applying cooperative multi-vessel systems (CMVSs) improve safety and efficiency urban waterway A framework consisting vessel train formation (VTF) intersection scheduling (CWIS) is proposed. Two types controllers are introduced. Intersection solve CWIS problems assign each a desired time arrival responsible for VTF segments timely at intersections. An alternating...

Autonomous underwater vehicles (AUVs) are widely used in sampling on-site the seawater parameters, such as temperature, salinity and biomass for better understanding ocean. The AUV path needs to be carefully planned order maximize sampled information within power constraints, which is known informative planning (IPP). existence of ocean currents further complicates problem. This article proposes an IPP method AUVs under influence via combining probabilistic roadmap <inline-formula...

The trajectory tracking control of unmanned surface vehicles (USVs) generally faces challenges from complex uncertain hydrodynamics and system constraints. In this paper, we leverage the capability Deep Neural Networks (DNN) in approximating arbitrary nonlinear dynamics, propose a hybrid physics-learning model based predictive (PL-MPC) method, Neural-sailing, for USVs. first feature PL-MPC is robust that it handles modeling errors caused by either USV or environmental disturbances....

This article considers intelligent fuel cell/battery hybrid vehicles (FCHVs) that can make autonomous decisions at both the vehicle and powertrain levels. Since level dynamics are inherently integrated, we propose an integrated motion model predictive control approach for FCHVs by jointly optimizing acceleration cell current. The goals to achieve mobility, minimal hydrogen consumption, battery state-of-charge maintenance within system constraints. main challenge in is electric motor operate...

Waterborne autonomous guided vessels (waterborne AGVs) moving over open waters experience environmental uncertainties. This paper proposes a novel cost-effective robust distributed control approach for waterborne AGVs. The overall system is uncertain and has independent subsystem dynamics but coupling objectives state constraints. AGVs determine their actions in parallel way, while still minimizing an cost function respecting constraints robustly by communicating within neighborhood. Our...

Abstract Since vessel dynamics could vary during maneuvering because of load changes, speed changing, environmental disturbances, aging mechanism, etc., the performance model‐based path following control may be degraded if controller uses same motion model all time. This article proposes an adaptive method based on least squares support vector machines (LS‐SVM) to deal with parameter changes model. The consists two components: online identification varying parameters and predictive (MPC)...

The rapidly developing computing and communication technologies improve the autonomy of individual vehicles on one hand facilitate coordination among other. In context dynamic speed management, this study considers a platoon intelligent that are required to maintain desired inter‐vehicle spaces respond changes in collision‐free, stable cooperative way. is modelled as cascaded network with linear longitudinal vehicle dynamics, independent physical constraints, coupling safety constraints....

In this paper, the scheduling of yard cranes (YCs) and external trucks (ETs) working in a U-shaped automated container terminal is proposed as new problem. This problem arises due to characteristic layout, where ETs enter through lanes interact with YCs. To formulate problem, three-objective optimization model established simultaneously schedule YCs ETs, considering their efficiencies. Its solution based on nondominated sorting genetic algorithm III (NSGA-III), which improved during...