DroneDiffusion: Robust Quadrotor Dynamics Learning with Diffusion Models

TL;DR

DroneDiffusion employs diffusion models to learn quadrotor dynamics, enhancing robustness and generalization in complex, real-world scenarios, and integrating with adaptive control for stable trajectory tracking.

Contribution

It introduces a novel diffusion-based framework for quadrotor dynamics learning, capturing complex uncertainties and improving robustness over existing methods.

Findings

Outperforms existing models in generalization to unseen scenarios

Demonstrates robustness in real-world flight conditions

Achieves stable trajectory tracking with adaptive control

Abstract

An inherent fragility of quadrotor systems stems from model inaccuracies and external disturbances. These factors hinder performance and compromise the stability of the system, making precise control challenging. Existing model-based approaches either make deterministic assumptions, utilize Gaussian-based representations of uncertainty, or rely on nominal models, all of which often fall short in capturing the complex, multimodal nature of real-world dynamics. This work introduces DroneDiffusion, a novel framework that leverages conditional diffusion models to learn quadrotor dynamics, formulated as a sequence generation task. DroneDiffusion achieves superior generalization to unseen, complex scenarios by capturing the temporal nature of uncertainties and mitigating error propagation. We integrate the learned dynamics with an adaptive controller for trajectory tracking with stability guarantees. Extensive experiments in both simulation and real-world flights demonstrate the robustness of the framework across a range of scenarios, including unfamiliar flight paths and varying payloads, velocities, and wind disturbances.