SwarmGPT: Combining Large Language Models with Safe Motion Planning for Drone Swarm Choreography
This work addresses the challenge of creating drone swarm choreographies for entertainment and safety-critical applications, offering a blueprint for integrating foundation models into swarm robotics, though it is incremental as it builds on existing LLM and motion planning methods.
The authors tackled the problem of designing safe and synchronized drone swarm choreographies by introducing SwarmGPT, a system that combines large language models with a safety filter for motion planning, enabling non-experts to create performances using natural language. They validated the approach with simulations of up to 200 drones and real-world experiments with up to 20 drones, demonstrating scalable and safe performances.
Drone swarm performances -- synchronized, expressive aerial displays set to music -- have emerged as a captivating application of modern robotics. Yet designing smooth, safe choreographies remains a complex task requiring expert knowledge. We present SwarmGPT, a language-based choreographer that leverages the reasoning power of large language models (LLMs) to streamline drone performance design. The LLM is augmented by a safety filter that ensures deployability by making minimal corrections when safety or feasibility constraints are violated. By decoupling high-level choreographic design from low-level motion planning, our system enables non-experts to iteratively refine choreographies using natural language without worrying about collisions or actuator limits. We validate our approach through simulations with swarms up to 200 drones and real-world experiments with up to 20 drones performing choreographies to diverse types of songs, demonstrating scalable, synchronized, and safe performances. Beyond entertainment, this work offers a blueprint for integrating foundation models into safety-critical swarm robotics applications.