Primary Investigator:
Ashok Raja

Project Members
Karthisri Meghana Guntupalli ; Ashok Vardhan Raja, Ph.D.

Recent advancements in Large Language Models (LLMs) have created new opportunities to integrate these models into robotics platforms, allowing unmanned aerial vehicles (UAVs) to have enhanced control and decision-making capabilities. The UAV market has experienced significant growth in recent years, accompanied by a surge in UAV-related job opportunities. The need for LLM-powered UAVs is expected to increase significantly as LLM technology develops. Therefore, it is essential to provide the upcoming generation of professionals, students, and educators with the knowledge and abilities they need to develop, implement, and operate LLM-driven UAV systems efficiently. However, there is a lack of education and training materials on LLM-powered UAVs, especially for hands-on practice. We propose a novel LLM-powered UAV laboratory platform that provides effective and efficient hands-on practice. Our laboratory platform comprises different simulation environments and preconfigured lab modules. The outcome of these lab modules is to educate and train users on LLM-powered advanced aerial route planning and perform vision-based cyber attack analysis. The lab platform will be open source, allowing other developers to customize it to their needs. Hence, our platform adopts a plug-in-based design to support customization of the lab modules. Our evaluation results show that our platform is effective and efficient in training and educating the students and professionals in operating LLM-powered UAV via natural language commands, develop task-specific customized prompts using prompt engineering techniques.