Key points are not available for this paper at this time.
Embodied intelligence is an emerging research field aimed at enabling intelligent agents to interact and collaborate with their environment in real-time. Large Language Models (LLMs) play a crucial role in the research and application paradigm of embodied intelligence. By utilizing LLMs as controllers, the powerful language processing capabilities can be leveraged to achieve planning and control of intelligent agents. This paper introduces and combines the open-source program PromptCraft released by Microsoft and the AirSim drone simulation platform to specifically describe how to construct a collaborative drone system using LLMs as controllers. The performance and effectiveness of the system are validated through experiments and case studies. By elucidating these findings, we gain deeper insights into the research and application paradigm of LLMs in the field of embodied intelligence. This provides valuable references and guidance for future intelligent agent design and development.
Zong et al. (Mon,) studied this question.