Design and implementation of AI chatbot for COLREGs training

Abstract

The education and training for the maritime industry require renewed focus in the face of technological changes and increasing digitalization. Artificial intelligence presents an avenue for further research that can positively impact efficiency and competence development. Among many applications of artificial intelligence in education, conversational agents or chatbots have gained increased interest in recent years. This paper describes the design and implementation process of “FLOKI”—a chatbot aimed at assisting maritime trainees in learning Collision Avoidance Regulations (COLREGs). For the design of the chatbot, IBM Watson Assistant®—a cognitive computing service—was utilized, which enables the use of Application Programming Interfaces (APIs) in its cloud server. A selected number (n = 18) of 2nd year B.Sc. in Nautical Science students in a Norwegian maritime university interacted with the chatbot for reflecting on their knowledge about COLREGs. In addition to demographic data, the maritime trainees were asked to answer questions related to user experience utilizing the System Usability Scale (SUS). The findings are discussed along with their implications and future research directions involving AI in maritime education and training.