Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX

2026-05-31

AI Summary

Existing drone simulation platforms struggle to simultaneously achieve high fidelity, differentiability, and support for large-scale swarms, hindering data-driven algorithm development from single-agent to multi-agent systems. This work proposes the first unified simulation framework built on JAX, integrating GPU acceleration, automatic differentiation, and lightweight system identification to deliver sub-centimeter trajectory accuracy and sampling efficiency exceeding 500 million steps per second. The platform enables parallel simulation of thousands of drones, maintains compatibility with real Crazyflie hardware, and—without relying on domain randomization—achieves high-precision control through on-board real-time reinforcement learning training completed in just 0.38 seconds. This approach substantially surpasses existing solutions in both simulation speed and deployment flexibility.

Abstract

High-quality, large-scale synthetic data from simulations is becoming a cornerstone for pushing the capabilities of robot algorithms. While aerial robotics simulators have evolved to support specialized needs such as fidelity, differentiability, and swarms independently, a unified platform that can synthesize data across all these domains is missing. In this work, we propose Crazyflow, a simulator designed to push the limits of aerial-robotics algorithm development, from model-based to data-driven methods, gradient-based to sampling-based approaches, and single-agent to multi-agent systems. Compared to existing state-of-the-art drone simulators, it achieves speeds more than an order of magnitude faster for a single drone and can simulate thousands of swarms of 4000 drones each. Real-world experiments show Crazyflow supports both analytical-gradient-based policy learning, achieving sub-centimeter trajectory tracking accuracy without domain randomization, and sampling-based obstacle avoidance at speeds exceeding half a billion steps per second. Breaking the traditional train-then-deploy paradigm, we show that its unprecedented speed even enables in-flight reinforcement learning; we demonstrate this by throwing a physical drone into the air and training a recovery policy from scratch in 0.38 seconds, successfully stabilizing the drone. Crazyflow supports multiple levels of simulation abstraction, is directly compatible with all open-source Crazyflie models, and enables rapid reconfiguration across custom drone platforms and applications by providing a light-weight system identification pipeline. By pushing accuracy, speed, and differentiability simultaneously, Crazyflow serves as an open-source resource for synthetic data generation, with emerging capabilities for large-scale parallelization for online, in-execution learning and optimization, opening the door to novel algorithm development.

Problem

• drone simulation
• differentiability
• swarm robotics
• synthetic data
• aerial robotics

Innovation

• differentiable simulation
• GPU acceleration
• in-flight reinforcement learning
• large-scale swarm simulation
• JAX-based robotics