Automatic Control With Human-Like Reasoning: Exploring Language Model Embodied Air Traffic Agents

TL;DR

This paper investigates the application of a language model-based agent with function-calling and learning capabilities to resolve air traffic conflicts without human intervention and reveals significant differences in performance across various configurations of the language model-based agents.

Abstract

Recent developments in language models have created new opportunities in air traffic control studies. The current focus is primarily on text and language-based use cases. However, these language models may offer a higher potential impact in the air traffic control domain, thanks to their ability to interact with air traffic environments in an embodied agent form. They also provide a language-like reasoning capability to explain their decisions, which has been a significant roadblock for the implementation of automatic air traffic control. This paper investigates the application of a language model-based agent with function-calling and learning capabilities to resolve air traffic conflicts without human intervention. The main components of this research are foundational large language models, tools that allow the agent to interact with the simulator, and a new concept, the experience library. An innovative part of this research, the experience library, is a vector database that stores synthesized knowledge that agents have learned from interactions with the simulations and language models. To evaluate the performance of our language model-based agent, both open-source and closed-source models were tested. The results of our study reveal significant differences in performance across various configurations of the language model-based agents. The best-performing configuration was able to solve almost all 120 but one imminent conflict scenarios, including up to four aircraft at the same time. Most importantly, the agents are able to provide human-level text explanations on traffic situations and conflict resolution strategies.

Figures (8)

• Figure 1: The language model embodied single agent setup
• Figure 2: Single Agent solving 3 aircraft conflicts without experience library. The LLM embodied agent automatically decides when and what commands (in green text) are to be invoked at all stages.
• Figure 3: The structure of the multiple language model embodied agent, containing planner, verifier, and executor agents.
• Figure 4: Creating the experience document from the operation logs of the agent
• Figure 5: Filtering and searching in the experience library based on experience embeddings