English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Bionic underwater robots have demonstrated their superiority in manyapplications. Yet, training their intelligence for a variety of tasks thatmimic the behavior of underwater creatures poses a number of challenges inpractice, mainly due to lack of a large amount of available training data aswell as the high cost in real physical environment. Alternatively, simulationhas been considered as a viable and important tool for acquiring datasets indifferent environments, but it mostly targeted rigid and soft body systems.There is currently dearth of work for more complex fluid systems interactingwith immersed solids that can be efficiently and accurately simulated for robottraining purposes. In this paper, we propose a new platform called "FishGym",which can be used to train fish-like underwater robots. The framework consistsof a robotic fish modeling module using articulated body with skinning, aGPU-based high-performance localized two-way coupled fluid-structureinteraction simulation module that handles both finite and infinitely largedomains, as well as a reinforcement learning module. We leveraged existingtraining methods with adaptations to underwater fish-like robots and obtainedlearned control policies for multiple benchmark tasks. The training results aredemonstrated with reasonable motion trajectories, with comparisons and analysesto empirical models as well as known real fish swimming behaviors to highlightthe advantages of the proposed platform.

FishGym: A High-Performance Physics-based Simulation Framework for Underwater Robot Learning