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/

Zendy Plus

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

Zendy Tools

Zendy Open

This paper proposes a realistic modularized framework for controllingautonomous surface vehicles (ASVs) on inland waterways (IWs) based on deepreinforcement learning (DRL). The framework improves operational safety andcomprises two levels: a high-level local path planning (LPP) unit and alow-level path following (PF) unit, each consisting of a DRL agent. The LPPagent is responsible for planning a path under consideration of dynamicvessels, closing a gap in the current research landscape. In addition, the LPPagent adequately considers traffic rules and the geometry of the waterway. Wethereby introduce a novel application of a spatial-temporal recurrent neuralnetwork architecture to continuous action spaces. The LPP agent outperforms astate-of-the-art artificial potential field (APF) method by increasing theminimum distance to other vessels by 65% on average. The PF agent performslow-level actuator control while accounting for shallow water influences andthe environmental forces winds, waves, and currents. Compared with aproportional-integral-derivative (PID) controller, the PF agent yields only 61%of the mean cross-track error (MCTE) while significantly reducing controleffort (CE) in terms of the required absolute rudder angle. Lastly, both agentsare jointly validated in simulation, employing the lower Elbe in northernGermany as an example case and using real automatic identification system (AIS)trajectories to model the behavior of other ships.

2-Level Reinforcement Learning for Ships on Inland Waterways: Path Planning and Following