Virtual Co-Pilot: Multimodal Large Language Model-enabled Quick-access Procedures for Single Pilot Operations

TL;DR

This paper introduces a Virtual Co-Pilot system powered by multimodal large language models to assist single pilots by quickly retrieving procedures and analyzing situations, aiming to enhance safety and reduce errors.

Contribution

It proposes a novel V-CoP concept utilizing multimodal LLMs for automated quick procedure searching in single-pilot operations, demonstrating promising preliminary results.

Findings

High accuracy in situational analysis (90.5%)

Effective retrieval of procedure information (86.5%)

Potential to reduce human errors in aviation

Abstract

Advancements in technology, pilot shortages, and cost pressures are driving a trend towards single-pilot and even remote operations in aviation. Considering the extensive workload and huge risks associated with single-pilot operations, the development of a Virtual Co-Pilot (V-CoP) is expected to be a potential way to ensure aviation safety. This study proposes a V-CoP concept and explores how humans and virtual assistants can effectively collaborate. A preliminary case study is conducted to explore a critical role of V-CoP, namely automated quick procedures searching, using the multimodal large language model (LLM). The LLM-enabled V-CoP integrates the pilot instruction and real-time cockpit instrumental data to prompt applicable aviation manuals and operation procedures. The results showed that the LLM-enabled V-CoP achieved high accuracy in situational analysis and effective retrieval of procedure information. The results showed that the LLM-enabled V-CoP achieved high accuracy in situational analysis (90.5%) and effective retrieval of procedure information (86.5%). The proposed V-CoP is expected to provide a foundation for future virtual intelligent assistant development, improve the performance of single pilots, and reduce the risk of human errors in aviation.