SwarmGPT: Combining Large Language Models with Safe Motion Planning for Drone Swarm Choreography

TL;DR

SwarmGPT uses large language models combined with safety filters to enable non-experts to design, refine, and deploy safe, synchronized drone swarm performances through natural language, validated in simulations and real-world tests.

Contribution

This work introduces SwarmGPT, a novel system integrating LLMs with safety filters for accessible drone choreography design, decoupling high-level planning from low-level motion control.

Findings

Successfully coordinated up to 200 drones in simulation.

Performed safe, synchronized drone shows with up to 20 drones in real-world experiments.

Demonstrated scalability and safety in diverse performance scenarios.

Abstract

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.