CHATATC: Large Language Model-Driven Conversational Agents for Supporting Strategic Air Traffic Flow Management
This work addresses the need for conversational AI support in non-safety-critical air traffic management, offering a domain-specific tool for professionals, though it is incremental as it applies existing LLM methods to a new dataset.
The researchers tackled the problem of deploying large language models (LLMs) in strategic air traffic flow management by training CHATATC on over 80,000 historical Ground Delay Program (GDP) records from 2000-2023, resulting in a system that successfully provides correct GDP details like rates and durations but has shortcomings with superlative questions.
Generative artificial intelligence (AI) and large language models (LLMs) have gained rapid popularity through publicly available tools such as ChatGPT. The adoption of LLMs for personal and professional use is fueled by the natural interactions between human users and computer applications such as ChatGPT, along with powerful summarization and text generation capabilities. Given the widespread use of such generative AI tools, in this work we investigate how these tools can be deployed in a non-safety critical, strategic traffic flow management setting. Specifically, we train an LLM, CHATATC, based on a large historical data set of Ground Delay Program (GDP) issuances, spanning 2000-2023 and consisting of over 80,000 GDP implementations, revisions, and cancellations. We test the query and response capabilities of CHATATC, documenting successes (e.g., providing correct GDP rates, durations, and reason) and shortcomings (e.g,. superlative questions). We also detail the design of a graphical user interface for future users to interact and collaborate with the CHATATC conversational agent.