The MOSES project reaches a highly succesful conclusion
Authors: Pantelis Papachristou, Konstantinos Nikolopoulos
13th March 2024
After 3 and a half years, the MOSES project has reached its culmination, marked by a closing conference held online. The central goal of the project was to enhance the Short Sea Shipping (SSS) component of the European container supply chain by implementing the following three groundbreaking innovations:
The development of a hybrid electric feeder vessel, equipped with a robotic container-handling system, to increase the utilisation rate of small ports.
The establishment of a digital collaboration and matchmaking platform to match demand and supply of cargo volumes, utilising Machine Learning (ML) to maximise Short Sea Shipping traffic.
The introduction of an autonomous vessel maneuvering and docking scheme, based on the cooperation of a swarm of autonomous tugboats coupled with an automated docking system.
Our role in the project
As part of the project, CORE has been involved in the third innovation concept, pioneering the transition from traditional docking procedures to an autonomous swarm of tugboats. These advancements were facilitated by creating a sophisticated simulation environment and the application of ML techniques, which refined docking strategies. This digital twin technology, coupled with an AutoPilot control system, exemplifies a significant leap forward in maritime operations, reducing docking time and enhancing port service availability and environmental sustainability.
Machine learning approach
Initially, our team created a virtual environment to simulate the real-life components, such as the port, water mass, tugboats and containership. To ensure fidelity to actual conditions, the virtual environment integrated results from hydrodynamic simulations conducted by MOSES partners, analysing the navigation and evaluating the hydrodynamic parameters, such as the friction resistances for each ship object separately. Additionally, Finite Element Model simulations (FEM) were employed to assess the interactions between the tugboats and the containership, by evaluating force-reactions and stresses.
MOSES Unity test scene displayed during training of 3 push agents next to the “Advanced Ship Controller” and “Behaviour parameters” component.
The simulation environment served as a training environment for the developed swarm intelligence machine learning algorithm, allowing agents to learn from their experiences. Specifically, the agents (tugboats) were trained using deep reinforcement learning techniques, where the learning procedure is based on the interaction of the agents with the environment and the accumulation of feedback (rewards or penalties), while the agents collected observations through LiDAR and GPS sensors. The goal was to discover optimal strategies that maximise cumulative rewards over time. The developed digital twin was deployed at the edge, along with an AutoPilot system to control the steering and thrust of the tugboats based on the digital twin’s inference.
The digital twin was successfully demonstrated and validated in relevant environment (TRL6) at the Faaborg port in Denmark, employing a swarm of two tugboats pushing a bargue towards the dock. The accompanying video below illustrates the precision of the simulation outcomes (displayed on the left-hand side) compared with the actual real-world demonstration (on the right-hand side). This live demonstration underscored a remarkable achievement: more than a 25% reduction in manoeuvring and docking times, leading to a corresponding significant decrease in port emissions and a notable increase in the availability of port services.
Comparison of the simulation outcomoes (left-hand side) with the real demonstration in Faaborg port (right-hand side) considering the scenario where two tugboats push a bargue to the dock.
The commercilisation phase
To ensure successful commercialisation, CORE developed an Innovation Strategy, focusing on clear value propositions and competition mapping. Additionally, CORE developed a model for profit simulation, with a focus on the innovations introduced by the autonomous tugboat system, which is the only technology solution combining autonomous operation, sustainability and safety, with the highest TRL and exposed in real conditions.
Understanding our pilot
For more information on Pilot 1 of the MOSES Project, where our technical team was heavily involved, our consortium partners have created a comprehensive video explaining the AutoDock System and how it works. You can watch it below.
Over the past 42 months, we were very happy to work closely with our consortium partners to successfully deliver an autonomous vessel manoeuvring and docking system which has the potential to completely transform the Short Sea Shipping and container supply chain of the European Union.
