LeRAAT: LLM-Enabled Real-Time Aviation Advisory Tool
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916658268864512 |
|---|---|
| author | Schlichting, Marc R. Rasmussen, Vale Alazzeh, Heba Liu, Houjun Jafari, Kiana Hardy, Amelia F. Asmar, Dylan M. Kochenderfer, Mykel J. |
| author_facet | Schlichting, Marc R. Rasmussen, Vale Alazzeh, Heba Liu, Houjun Jafari, Kiana Hardy, Amelia F. Asmar, Dylan M. Kochenderfer, Mykel J. |
| contents | In aviation emergencies, high-stakes decisions must be made in an instant. Pilots rely on quick access to precise, context-specific information -- an area where emerging tools like large language models (LLMs) show promise in providing critical support. This paper introduces LeRAAT, a framework that integrates LLMs with the X-Plane flight simulator to deliver real-time, context-aware pilot assistance. The system uses live flight data, weather conditions, and aircraft documentation to generate recommendations aligned with aviation best practices and tailored to the particular situation. It employs a Retrieval-Augmented Generation (RAG) pipeline that extracts and synthesizes information from aircraft type-specific manuals, including performance specifications and emergency procedures, as well as aviation regulatory materials, such as FAA directives and standard operating procedures. We showcase the framework in both a virtual reality and traditional on-screen simulation, supporting a wide range of research applications such as pilot training, human factors research, and operational decision support. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16477 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LeRAAT: LLM-Enabled Real-Time Aviation Advisory Tool Schlichting, Marc R. Rasmussen, Vale Alazzeh, Heba Liu, Houjun Jafari, Kiana Hardy, Amelia F. Asmar, Dylan M. Kochenderfer, Mykel J. Human-Computer Interaction Artificial Intelligence Emerging Technologies Information Retrieval J.2; H.3.3; H.5.0 In aviation emergencies, high-stakes decisions must be made in an instant. Pilots rely on quick access to precise, context-specific information -- an area where emerging tools like large language models (LLMs) show promise in providing critical support. This paper introduces LeRAAT, a framework that integrates LLMs with the X-Plane flight simulator to deliver real-time, context-aware pilot assistance. The system uses live flight data, weather conditions, and aircraft documentation to generate recommendations aligned with aviation best practices and tailored to the particular situation. It employs a Retrieval-Augmented Generation (RAG) pipeline that extracts and synthesizes information from aircraft type-specific manuals, including performance specifications and emergency procedures, as well as aviation regulatory materials, such as FAA directives and standard operating procedures. We showcase the framework in both a virtual reality and traditional on-screen simulation, supporting a wide range of research applications such as pilot training, human factors research, and operational decision support. |
| title | LeRAAT: LLM-Enabled Real-Time Aviation Advisory Tool |
| topic | Human-Computer Interaction Artificial Intelligence Emerging Technologies Information Retrieval J.2; H.3.3; H.5.0 |
| url | https://arxiv.org/abs/2503.16477 |