Deep Interactive Reinforcement Learning for Path Following of Autonomous Underwater Vehicle

Zhang, Qilei; Lin, Jinying; Sha, Qixin; Li, Guangliang

doi:10.48550/arxiv.2001.03359

Cited by 1 publication

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep Reinforcement Learning (DRL) controller was developed for different types of applications (i.e. to solve the BlueROV2 station Keeping UUV simulator citations for each application type [109] or tracking problem [110]). DRL controller was also compared with PID in the Start-end Point task in the presence of various ocean currents [111].…”

Section: B Uuv Simulatormentioning

confidence: 99%

Underwater Simulators Analysis for Digital Twinning

Ciuccoli,

Screpanti,

Scaradozzi

2024

IEEE Access

View full text Add to dashboard Cite

The underwater environment is among Earth's most challenging domains, where failures incur elevated risks and costs for both technology and human endeavors. As a consequence, forecasting the behavior of mechatronic systems through simulation has become increasingly important. Underwater Robotic Simulators (URSs) allow researchers and engineers to safely develop and assess submarine systems. The selection of an appropriate URS from the list of available tools is not trivial. Moreover, the integration of this software with the Digital Twin (DT) concept presents numerous advantages, particularly the ability to link the simulated environment with actual underwater vehicles. This connection is facilitated by performing validation and simulation tests using Software In the Loop (SIL), Model In the Loop, and Hardware In the Loop (HIL) techniques. This paper extensively reviews URSs in the context of both robots and unmanned vehicles in light of the DT paradigm. The article critically examines distinctions among existing URSs, offering valuable insights to aid researchers in selecting the most fitting tool for their specific applications. Additionally, the review explores the practical applications of the identified simulators, categorizing their usage across different fields to illuminate the preferences within the scientific community and showcase prominent case studies.

show abstract

Section: B Uuv Simulatormentioning

confidence: 99%