A Generalized Simulation Framework for Tethered Remotely Operated Vehicles in Realistic Underwater Environments (2018)
Type of ContentJournal Article
This paper presents a framework for simulating visually realistic motion of underwater Remotely Operated Vehicles (ROVs) in highly complex models of aquatic environments. The models include a wide range of objects such as rocks, fish and marine plankton in addition to an ROV tether. A modified cable simulation for the underwater physical conditions has been developed for a tethered ROV. The simulation framework also incorporates models for low visibility conditions and intrinsic camera effects unique to the underwater environment. The visual models were implemented using the Unreal Engine 4 realistic game engine to be part of the presented framework. We developed a generalized method for implementing an ROV dynamics model and this method serves as a highly configurable component inside our framework. In this paper, we explore the unique characteristics of underwater simulation and the specialized models we developed for that environment. We use computer vision algorithms for feature extraction and feature tracking as a probe for comparing experiments done in our simulated environment against real underwater experiments. The experimental results presented in this paper successfully demonstrate the contribution of this realistic simulation framework to the understanding, analysis and development of computer vision and control algorithms to be used in today’s ROVs.
CitationGanoni O, Mukundan R, Green R A Generalized Simulation Framework for Tethered Remotely Operated Vehicles in Realistic Underwater Environments. Drones. 3(1). 1-1.
This citation is automatically generated and may be unreliable. Use as a guide only.
Keywordsrobot simulation; ROV; underwater simulation; cable simulation; Unreal Engine 4; plankton; dynamic simulation
ANZSRC Fields of Research40 - Engineering::4015 - Maritime engineering::401505 - Special vehicles
46 - Information and computing sciences::4602 - Artificial intelligence::460207 - Modelling and simulation
RightsThis article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Showing items related by title, author, creator and subject.
A Framework for Visually Realistic Multi-robot Simulation in Natural Environment Ganoni O; Mukundan R (University of West Bohemia, 2017)This paper presents a generalized framework for the simulation of multiple robots and drones in highly realistic models of natural environments. The proposed simulation architecture uses the Unreal Engine4 for generating ...
Integrating Equity Considerations into Agent-Based Modeling: A Conceptual Framework and Practical Guidance Williams TG; Brown DG; Guikema SD; Magliocca NR; Müller B; Steger CE; Logan, Thomas (Journal of Artificial Societies and Social Simulation, 2022)Advancing equity is a complex challenge for society, science, and policy. Agent-based models are increasingly used as scientific tools to advance understanding of systems, inform decision-making, and share knowledge. ...
Loss of Significance and Its Effect on Point Normal Orientation and Cloud Registration Young M; Pretty C; Agostinho S; Green R; Chen X (MDPI AG, 2019)Point normal calculation and cloud registration are two of the most common operations in point cloud processing. However, both are vulnerable to issues of numerical precision and loss of significance. This paper documents ...