Together with Force Technologies we defined the best possible technical roadmap for a long-term AI initiative on how to teach an AI-model to navigate ships using Inverse Reinforcement Learning.
Together with Force Technologies we defined the best possible technical roadmap for a long-term AI initiative on how to teach an AI-model to navigate ships using Inverse Reinforcement Learning.
Challenge
Lack of a clear roadmap for AI adoption and how to start a long-term AI initiative.
Solution
Validated the approach and accelerated the project by reducing time-consuming methodology research and piloting.
Result
Clear roadmap for implementing AI in their long term strategy.
"Halfspace saved us months of research trying to find the right approach. Halfspace pointed out the way forward both in the short and long term, giving a more efficient way forward and no doubt a better end product"
Bugge Jensen, Senior Project Manager, Force
Bringing AI to the sea
A ship simulation center is one of the many services offered by FORCE Technology, a leading international non-profit technological consulting and service company. Recently, FORCE Technology has begun a long-term project to develop a ship simulator that uses artificial intelligence to navigate without a human captain. The vision is to build and train an AI model that is able to:
1. Berth a ship in a given port in a ship simulator under varying weather conditions, using various ship types.
2. Emulate how human captains would behave using a large dataset of historical simulations.
FORCE Technology wanted assistance in breaking down this complex vision and guidance for building an AI agent. Having no clear roadmap for AI adoption was the main challenge: Where and how to begin a long-term AI project.
Finding the best use case
Over the course of five weeks, FORCE Technology and Halfspace combined their expertise in ship simulations and AI methodologies. We aimed to define the best technical roadmap for the long-term AI initiative: how to teach an AI model to navigate using inverse reinforcement learning (RL). Inverse RL allows AI agents to learn from human experts' behavior by simply watching and emulating them.
A roadmap for implementation
By validating the approach and reducing time-consuming methodology research and piloting, Halfspace helped FORCE Technology make a complex AI vision more actionable.
For major AI initiatives to succeed, it is crucial to get off to a good start. At these early stages, however, many long-term factors must be considered carefully to ensure an efficient process and the right approach to AI that can be operationalised. With a thoroughly vetted and actionable roadmap, FORCE Technology is well-prepared to launch its AI initiative.
A successful AI initiative requires a good start. It is crucial to consider many long-term factors at these early stages to ensure an efficient process and an appropriate AI approach. Building an actionable and well-vetted roadmap is essential for a company to launch its AI initiative effectively.
Unlock your organisation's potential with AI and advanced analytics