Skip to main content
SpringerLink
Log in

Towards Using Reinforcement Learning for Autonomous Docking of Unmanned Surface Vehicles

  • Conference paper
  • First Online:
Engineering Applications of Neural Networks (EANN 2022)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1600))

Abstract

Providing full autonomy to Unmanned Surface Vehicles (USV) is a challenging goal to achieve. Autonomous docking is a subtask that is particularly difficult. The vessel has to distinguish between obstacles and the dock, and the obstacles can be either static or moving. This paper developed a simulator using Reinforcement Learning (RL) to approach the problem.

We studied several scenarios for the task of docking a USV in a simulator environment. The scenarios were defined with different sensor inputs and start-stop procedures but a simple shared reward function. The results show that the system solved the task when the IMU (Inertial Measurement Unit) and GNSS (Global Navigation Satellite System) sensors were used to estimate the state, despite the simplicity of the reward function.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://github.com/udacity/self-driving-car-sim.

  2. 2.

    https://anonymous.4open.science/r/boatSimulator-3605/.

  3. 3.

    https://anonymous.4open.science/r/SteeringDockingPaper-98BC/README.md.

References

  1. ml-agents/gym-unity at main Unity-Technologies/ml-agents. https://github.com/Unity-Technologies/ml-agents/tree/main/gym-unity

  2. Andrychowicz, M., et al.: What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study, June 2020. http://arxiv.org/abs/2006.05990

  3. Badue, C., et al.: Self-driving cars: a survey. Expert Syst. Appl. 165, 113816 (2021). https://doi.org/10.1016/J.ESWA.2020.113816

    Article  Google Scholar 

  4. Bjering Strand, H.: Autonomous docking control system for the otter USV: a machine learning approach (2020). https://ntnuopen.ntnu.no/ntnu-xmlui/handle/11250/2780950

  5. Brockman, G., et al.: OpenAI Gym, June 2016. https://arxiv.org/abs/1606.01540v1

  6. Castro, P.S., Moitra, S., Gelada, C., Kumar, S., Bellemare, M.G.: Dopamine: a research framework for deep reinforcement learning, December 2018. https://arxiv.org/abs/1812.06110v1

  7. Cui, R., Yang, C., Li, Y., Sharma, S.: Adaptive neural network control of AUVs with control input nonlinearities using reinforcement learning. IEEE Trans. Syst. Man Cybern. Syst. 47(6), 1019–1029 (2017). https://doi.org/10.1109/TSMC.2016.2645699

  8. Cui, Y., Osaki, S., Matsubara, T.: Autonomous boat driving system using sample-efficient model predictive control-based reinforcement learning approach. J. Field Robot. 38(3), 331–354 (2021). https://doi.org/10.1002/ROB.21990

    Article  Google Scholar 

  9. Dosovitskiy, A., Ros, G., Codevilla, F., López, A., Koltun, V.: CARLA: an open urban driving simulator. In: Conference on robot learning, pp. 1–16 (2017)

    Google Scholar 

  10. Epic Games, I.: The most powerful real-time 3D creation tool - unreal Engine. https://www.unrealengine.com/en-US/

  11. Fossen, T.I.: Handbook of Marine Craft Hydrodynamics and Motion Control, 2nd Edition. 2nd edn. Wiley, Hoboken, April 2021

    Google Scholar 

  12. Gaudet, B., Linares, R., Furfaro, R.: Deep reinforcement learning for six degree-of-freedom planetary landing. Adv. Space Res. 65(7), 1723–1741 (2020). https://doi.org/10.1016/J.ASR.2019.12.030

    Article  Google Scholar 

  13. Juliani, A., et al.: Unity: a general platform for intelligent agents, September 2018. https://arxiv.org/abs/1809.02627v2

  14. Koenig, N., Howard, A.: Design and use paradigms for Gazebo, an open-source multi-robot simulator. In: 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), vol. 3, pp. 2149–2154 (2004). https://doi.org/10.1109/IROS.2004.1389727

  15. Kretschmann, L., Burmeister, H.C., Jahn, C.: Analyzing the economic benefit of unmanned autonomous ships: an exploratory cost-comparison between an autonomous and a conventional bulk carrier. Res. Transp. Bus. Manage. 25, 76–86 (2017). https://doi.org/10.1016/J.RTBM.2017.06.002

  16. Kyriakidis, M., et al.: A human factors perspective on automated driving. 20(3), 223–249 (2017). https://doi.org/10.1080/1463922X.2017.1293187, https://www.tandfonline.com/doi/abs/10.1080/1463922X.2017.1293187

  17. Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings, September 2015. https://arxiv.org/abs/1509.02971v6

  18. Martinsen, A.B., Lekkas, A.M.: Straight-Path following for underactuated marine vessels using deep reinforcement learning. IFAC-PapersOnLine 51(29), 329–334 (2018). https://doi.org/10.1016/J.IFACOL.2018.09.502

  19. Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015). https://doi.org/10.1038/nature14236, https://www.nature.com/articles/nature14236

  20. Moerland, T.M., Broekens, J., Plaat, A., Jonker, C.M.: A0C: alpha zero in continuous action space, May 2018. https://arxiv.org/abs/1805.09613v1

  21. Mousazadeh, H., et al.: Developing a navigation, guidance and obstacle avoidance algorithm for an unmanned surface vehicle (USV) by algorithms fusion. Ocean Eng. 159, 56–65 (2018). https://doi.org/10.1016/J.OCEANENG.2018.04.018

    Article  Google Scholar 

  22. OpenAI: openai/baselines: OpenAI Baselines: high-quality implementations of reinforcement learning algorithms. https://github.com/openai/baselines

  23. Pomerleau, D.A.: Alvinn: an autonomous land vehicle in a neural network. Adv. Neural Inf. Process. Syst. (1989). https://proceedings.neurips.cc/paper/1988/file/812b4ba287f5ee0bc9d43bbf5bbe87fb-Paper.pdf

  24. Rai, R.: Socket. IO Real-Time Web Application Development - Rohit Rai - Google Books. Packt Publishing Ltd., Birmingham, 1st edn., February 2013. https://books.google.no/books?id=YgdbZbkTDkoC&pg=PT37&dq=socket+io&lr=&source=gbs_selected_pages&cad=2#v=onepage&q=socket%20io&f=false

  25. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms, July 2017. https://arxiv.org/abs/1707.06347v2

  26. Shao, G., Ma, Y., Malekian, R., Yan, X., Li, Z.: A novel cooperative platform design for coupled USV-UAV systems. IEEE Trans. Ind. Inf. 15(9), 4913–4922 (2019). https://doi.org/10.1109/TII.2019.2912024

    Article  Google Scholar 

  27. Shuai, Y., et al.: An efficient neural-network based approach to automatic ship docking. Ocean Eng. 191, 106514 (2019). https://doi.org/10.1016/J.OCEANENG.2019.106514

    Article  Google Scholar 

  28. Tang, Y., Agrawal, S.: Discretizing continuous action space for on-policy optimization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 5981–5988, April 2020. https://doi.org/10.1609/AAAI.V34I04.6059, https://ojs.aaai.org/index.php/AAAI/article/view/6059

  29. Thor I. Fossen: Lecture Notes: TTK 4190 Guidance, Navigation and Control of vehicles. https://www.fossen.biz/wiley/pdf/Ch1.pdf

  30. Unity: Unity - Manual: GameObjects. https://docs.unity3d.com/Manual/GameObjects.html

  31. Van Hasselt, H., Wiering, M.A.: Reinforcement learning in continuous action spaces. In: Proceedings of the 2007 IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning, ADPRL 2007, pp. 272–279 (2007). https://doi.org/10.1109/ADPRL.2007.368199

  32. Vásárhelyi, G., Virágh, C., Somorjai, G., Nepusz, T., Eiben, A.E., Vicsek, T.: Optimized flocking of autonomous drones in confined environments. Sci. Robot. 3(20) (2018). https://doi.org/10.1126/SCIROBOTICS.AAT3536/SUPPL_FILE/AAT3536_SM.PDF, https://www.science.org/doi/abs/10.1126/scirobotics.aat3536

  33. Veelen, M.v., Spreij, P.: Evolution in games with a continuous action space Matthijs van Veelen \(\cdot \) Peter Spreij (2008). https://doi.org/10.1007/s00199-008-0338-8

  34. Zhang, P., et al.: Reinforcement learning-based end-to-end parking for automatic parking system. Sensors 19(18), 3996 (2019). https://doi.org/10.3390/S19183996, https://www.mdpi.com/1424-8220/19/18/3996/htm www.mdpi.com/1424-8220/19/18/3996

Download references

Author information

Authors and Affiliations

  1. Centre for Artificial Intelligence Research, University of Agder, Kristiansand, Norway

    Martin Holen & Morten Goodwin

  2. Norwegian Defence Research Establishment (FFI), Kjeller, Norway

    Else-Line Malene Ruud & Narada Dilp Warakagoda

  3. Institute for Technology Systems, University of Oslo, Oslo, Norway

    Narada Dilp Warakagoda & Paal Engelstad

  4. Top Research Centre Mechatronics, University of Agder, Kristiansand, Norway

    Kristian Muri Knausgård

Authors
  1. Martin Holen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Else-Line Malene Ruud
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Narada Dilp Warakagoda
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Morten Goodwin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Paal Engelstad
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kristian Muri Knausgård
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Martin Holen .

Editor information

Editors and Affiliations

  1. Democritus University of Thrace, Xanthi, Greece

    Lazaros Iliadis

  2. Teesside University, Middlesbrough, UK

    Chrisina Jayne

  3. Aristotle University of Thessaloniki, Thessaloniki, Greece

    Anastasios Tefas

  4. University of the West of England, Bristol, UK

    Elias Pimenidis

Rights and permissions

Reprints and permissions

Copyright information

© 2022 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Holen, M., Ruud, EL.M., Warakagoda, N.D., Goodwin, M., Engelstad, P., Knausgård, K.M. (2022). Towards Using Reinforcement Learning for Autonomous Docking of Unmanned Surface Vehicles. In: Iliadis, L., Jayne, C., Tefas, A., Pimenidis, E. (eds) Engineering Applications of Neural Networks. EANN 2022. Communications in Computer and Information Science, vol 1600. Springer, Cham. https://doi.org/10.1007/978-3-031-08223-8_38

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-08223-8_38

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-08222-1

  • Online ISBN: 978-3-031-08223-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation