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

Accurate control of autonomous marine robots still poses challenges due tothe complex dynamics of the environment. In this paper, we propose a DeepReinforcement Learning (DRL) approach to train a controller for autonomoussurface vessel (ASV) trajectory tracking and compare its performance with anadvanced nonlinear model predictive controller (NMPC) in real environments.Taking into account environmental disturbances (e.g., wind, waves, andcurrents), noisy measurements, and non-ideal actuators presented in thephysical ASV, several effective reward functions for DRL tracking controlpolicies are carefully designed. The control policies were trained in asimulation environment with diverse tracking trajectories and disturbances. Theperformance of the DRL controller has been verified and compared with the NMPCin both simulations with model-based environmental disturbances and in naturalwaters. Simulations show that the DRL controller has 53.33% lower trackingerror than that of NMPC. Experimental results further show that, compared toNMPC, the DRL controller has 35.51% lower tracking error, indicating that DRLcontrollers offer better disturbance rejection in river environments than NMPC.

Deep Reinforcement Learning Based Tracking Control of an Autonomous Surface Vessel in Natural Waters