SwarmGPT: Combining Large Language Models with Safe Motion Planning for Drone Swarm Choreography
Martin Schuck, Dinushka Orrin Dahanaggamaarachchi, Ben Sprenger, Vedant Vyas, Siqi Zhou, Angela P. Schoellig
AI summary
Problem
Designing smooth, safe, and synchronized choreographies for drone swarms is labor-intensive and requires significant expert knowledge to balance artistic expression with hardware constraints and collision avoidance.
Approach
The system decouples high-level choreographic design from low-level motion planning by using an LLM to generate language-driven choreographies, which are then corrected by a distributed optimization-based safety filter to ensure collision-free and physically feasible trajectories.
Key results
- Language-driven choreography generation using LLMs and motion primitives
- Distributed optimization-based safety filter for real-time collision avoidance
- Successful simulations with up to 200 drones and real-world experiments with 20 drones
- Effective natural language reprompting for iterative choreography refinement
Why it matters
Provides a scalable blueprint for safely integrating foundation models into safety-critical swarm robotics applications beyond entertainment.
Abstract
Drone swarm performances—synchronized, expres- sive aerial displays set to music—have emerged as a captivating application of modern robotics. Yet designing smooth, safe chore- ographies 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.