Air pollution is one of the innumerable menaces an individual comes across every moment. Countless means to make urban lives smoother are indebted to witnessing air pollution and other types of pollution. It is contri...
详细信息
Numerous advancements have been identified as potentially disruptive innovations in the surgical workplace as surgical workflow continues to improve in the digital age. The application of virtual reality (VR) and augm...
详细信息
The types of collisions during road crashes and the factors contributing to them are many. Chances of collisions can be reduced by predicting the probability of types of collisions at various locations and providing d...
详细信息
This paper focuses on studying and analyzing the kinematics characteristics of the Naval Ship Survival Training Simulation System (NSSTSS) in the case of longitudinal shake of the anti-sinking chamber on the ship. Bas...
详细信息
Deep Learning (DL), especially with Large Language Models (LLMs), brings benefits to various areas. However, DL training systems usually yield prominent idling GPU resources due to many factors, such as resource alloc...
详细信息
The persistent traffic congestion in Dhaka, Bangladesh, calls for innovative and efficient solutions tailored to its unique urban dynamics. This study introduces a novel approach to traffic bottleneck identification t...
详细信息
With the increasing number of end users that are using multimedia services, demand for access network high bitrate systems with sufficient quality of services also increases. However, this might not always be ensured ...
详细信息
Given the increasing prevalence of deep learning applications in dermatological disease diagnosis, the pursuit of diagnostic accuracy needs to be accompanied by a focus on decision-making fairness to avoid unfair disc...
详细信息
With the increasing integration of AGVs (Automated Guided Vehicles) and Robot Arms in manufacturing systems, traditional scheduling approaches that handle them separately often lead to inefficiencies and poor coordina...
详细信息
Over the last decade, Unmanned Surface Vehicles (USVs) have gained significant traction in marine scientific research and military domains. Given the necessity for extensive coverage in many missions, the deployment o...
详细信息
ISBN:
(纸本)9789819607730;9789819607747
Over the last decade, Unmanned Surface Vehicles (USVs) have gained significant traction in marine scientific research and military domains. Given the necessity for extensive coverage in many missions, the deployment of multiple USVs for coordinated operations has emerged as a viable strategy. This study presents a novel model-free deep reinforcement learning (DRL) approach for coordinating multiple USVs, with a particular emphasis on ensuring formation stability. First, a dynamic model for formation navigation in a non-stationary stochastic ocean environment is derived, accounting for both acceleration and angular velocity control. Next, a hierarchical leader-follower architecture is designed, facilitating the formation of stable chain formations and simplifying the control challenge. To address the complex, nonlinear coupling issues, deep reinforcement learning methods are employed, specifically the deep deterministic policy gradient (DDPG) and double deep Q-network (DDQN), both utilizing deep neural network (DNN) approximations. The comparative analysis of these methods in simulation showcases the effectiveness of the proposed control strategy and the adaptability of USVs in maintaining formation navigation even in non-stationary random environments.
暂无评论