To alleviate the pressure on crew members in the lookout and warning tasks during ship navigation, this research developed a ship electronic lookout (SEL) using the Low-Rank Adaption (LoRA) fine-tuned Large Language Model (LLM). The SEL can synthesize heterogeneous information from multiple sensors, such as CCTV and AIS, to depict the current navigation environment in real-time and provide lookout alerts. Specifically, real-world navigation data is first collected, and the sensor information is processed into a dataset (LookOut). Subsequently, Qwen2-7B-Instruct was selected as the baseline to balance model responsiveness and safety. Finally, LoRA was used for supervised fine-tuning (SFT) to develop the SEL. Experimental demonstrate that LLM fine-tuned for specific application scenarios can mimic the language norms of the ship lookout and be combined with perception systems to achieve electronic lookout.
Developing Ship Electronic Lookout Using LoRA Fine-Tuned Large Language Model
Lect. Notes Electrical Eng.
International Conference on Artificial Intelligence and Autonomous Transportation ; 2024 ; Beijing, China December 06, 2024 - December 08, 2024
The Proceedings of 2024 International Conference on Artificial Intelligence and Autonomous Transportation ; Chapter : 15 ; 157-164
2025-03-31
8 pages
Article/Chapter (Book)
Electronic Resource
English
Ship lookout platform structure, construction method thereof and ship
European Patent Office | 2024
|NTIS | 2000
|Mariner's Behavioral Characteristics of Lookout on Traffic - The Range of Lookout -
British Library Online Contents | 2015
|British Library Online Contents | 1997