AI for cargo stowage

RoRo (Roll-on/Roll-off) vessels carry 234 million tonnes of goods annually around Europe, and is growing at an average rate of 3%.[1,2] RoRo vessels follow fixed routes between ports, and ferry cargo, mainly vehicles, across the sea. RoRo cargo arrives shortly before departure and is loaded in a hurry.

The task of the RoRo cargo stowage planner is to limit delays and to ensure a good balance of the cargo onboard for each trip.[2] The stowage planners thus face a combinatorial explosion of potential arrangements. They must quickly coordinate loading, and determine a suitable arrangement for both placement and weight of cargo.[3] Suboptimal arrangements are costing shipping companies millions per year, as a more balanced ship will provide fuel (and emissions) savings of up to 2% per trip.[3,4,5]

Commercial stowage planning software dedicated to RoRo ships already exist. They provide a visual aid for cargo planners, but fall short of providing decision support in terms of calculating stowage plan options.[6] Using machine learning (ML) and deep learning (DL), Artificial Intelligence (AI) offers an algorithmic approach to support stowage optimization, calculating and suggesting options for the stowage planner.[6] AI and digitalization also have the potential to provide a better service to clients by providing them with a more accurate time of when cargo will be discharged. Nevertheless, questions remain over the feasibility of integrating the technology.

When will AI be used to support the cargo stowage planner in RoRo operations?

Take the survey & get involved

[1] ECSA (2016), Short Sea Shipping - The full potential yet to be unleashed
[2] European Commision (2015), Analysis of Recent Trends in EU Shipping and Analysis and Policy Support to Improve the Competetiveness of Short Sea Shipping in the EU
[3] Kemp, S., Roach, P., Ware, A., Wilson, I., & Univ of Glamorgan (2003), Artificial Intelligence for Automatic Container Stowage Planning Optimisation
[4] Hochkirch, K. & Bertram, V. (2010), Engineering Options for More Fuel Efficient Ships
[5] FuchsTechnology (2012), Reducing Fuel Consumption on Cruise Vessels
[6] Wathne, E. (2012), Cargo Stowage Planing in RoRo Shipping
[7] Martinez, C. (2020), Artificial Intelligence
More Information:
Wilson, I., Roach, P. & Ware, J. (2001), Container Stowage Pre-planning: using search to generate solutions, a case study
Wei-ying, Z., Yan, L. & Zhuo-shang, J. (2005), Model and algorithm for container ship stowage planning based on bin-packing problem
Santosa, M. & Santosa, B. (2017), Solving the Container Stowage Problem (CSP) using Particle Swarm Optimiztion (PSO)
Martin, R. (2019), How AI & Automation Has Overhauled The Shipping Industry
Samulel, A. & Sivadas, N. (2019), Artificial Intelligence and the marine industry
ParkingDetection (2020), Smart parking with artificial intelligence
Bosch (2020), Thinking outside the box with artificial intelligence
Tang, G. & Guo, Z. (2015), Simulation and Modelling of Roll-on/Roll-off Terminal Operation
Fusco, P., Saurí, S. & Spuch, B. (2010), Quality indicators and capacity calculation for RoRo terminals
Mishra, B. (2019), Artificial Intelligence and the Shipping Industry

By Matthew J. Spaniol