Reproduce “Underwater Robotic Simulators Review for Autonomous System Development” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sara Aldhaheri, Yang Hu, Yongchang Xie, Peng Wu, Dimitrios Kanoulas, Yuanchang Liu
Researchers from UCL and TII review and comparatively analyze five state-of-the-art open-source underwater robotic simulators (Stonefish, DAVE, HoloOcean, MARUS, UNav-Sim). The analysis evaluates them based on architectural design, sensor and physics modeling, task capabilities, and research impact to guide simulator selection and highlight future development areas, particularly concerning the sim-to-real gap and the need for standardization.
Key insights
- Each reviewed URS (Stonefish, DAVE, HoloOcean, MARUS, UNav-Sim) possesses distinct strengths and applications, making selection dependent on specific research needs.
- Despite advancements in high-fidelity simulation, a significant sim-to-real gap persists, emphasizing the need for incorporating deliberate disturbances and realistic sensor inaccuracies.
- There is a critical need for standardization, particularly for reinforcement learning in underwater robotics, to improve reproducibility, benchmarking, and collaborative research.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.