Next Article in Journal
A Critical Review of a Holistic Model Used for Assessing Multimodal Transport Systems
Previous Article in Journal
Prioritized Solutions for Overcoming Barriers When Implementing Lean in the Healthcare Supply Chain: A Saudi Perspective
Article

Rolling Cargo Management Using a Deep Reinforcement Learning Approach

1
Department of Computer Science, Jönköping University, 553 18 Jönköping, Sweden
2
Department of Pharmaceutical Biosciences, Uppsala University, 752 36 Uppsala, Sweden
3
Stena Line, 413 27 Göteborg, Sweden
4
Centre for Reliable Machine Learning, University of London, London WC1E 7HU, UK
*
Authors to whom correspondence should be addressed.
Academic Editor: Noel Greis
Received: 27 November 2020 / Revised: 28 January 2021 / Accepted: 31 January 2021 / Published: 8 February 2021
Loading and unloading rolling cargo in roll-on/roll-off are important and very recurrent operations in maritime logistics. In this paper, we apply state-of-the-art deep reinforcement learning algorithms to automate these operations in a complex and real environment. The objective is to teach an autonomous tug master to manage rolling cargo and perform loading and unloading operations while avoiding collisions with static and dynamic obstacles along the way. The artificial intelligence agent, representing the tug master, is trained and evaluated in a challenging environment based on the Unity3D learning framework, called the ML-Agents, and using proximal policy optimization. The agent is equipped with sensors for obstacle detection and is provided with real-time feedback from the environment thanks to its own reward function, allowing it to dynamically adapt its policies and navigation strategy. The performance evaluation shows that by choosing appropriate hyperparameters, the agents can successfully learn all required operations including lane-following, obstacle avoidance, and rolling cargo placement. This study also demonstrates the potential of intelligent autonomous systems to improve the performance and service quality of maritime transport. View Full-Text
Keywords: deep reinforcement learning; cargo management for roll-on/roll-off ships; autonomous tug master; agent based reinforcement learning; collision avoidance deep reinforcement learning; cargo management for roll-on/roll-off ships; autonomous tug master; agent based reinforcement learning; collision avoidance
Show Figures

Figure 1

MDPI and ACS Style

Oucheikh, R.; Löfström, T.; Ahlberg, E.; Carlsson, L. Rolling Cargo Management Using a Deep Reinforcement Learning Approach. Logistics 2021, 5, 10. https://0-doi-org.brum.beds.ac.uk/10.3390/logistics5010010

AMA Style

Oucheikh R, Löfström T, Ahlberg E, Carlsson L. Rolling Cargo Management Using a Deep Reinforcement Learning Approach. Logistics. 2021; 5(1):10. https://0-doi-org.brum.beds.ac.uk/10.3390/logistics5010010

Chicago/Turabian Style

Oucheikh, Rachid, Tuwe Löfström, Ernst Ahlberg, and Lars Carlsson. 2021. "Rolling Cargo Management Using a Deep Reinforcement Learning Approach" Logistics 5, no. 1: 10. https://0-doi-org.brum.beds.ac.uk/10.3390/logistics5010010

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop