# Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors

## TL;DR

This paper demonstrates that reinforcement learning can be used to train low-level quadrotor control policies in simulation that transfer effectively to multiple real-world quadrotors, showing robustness and generalization without traditional controllers.

## Contribution

It introduces a novel approach using reinforcement learning to develop low-level, robust quadrotor controllers that generalize across different physical drones, without relying on stabilizing PD controllers.

## Key findings

- Policies are robust to external disturbances.
- Controllers transfer successfully to multiple quadrotors.
- Training methodologies influence flight performance.

## Abstract

Quadrotor stabilizing controllers often require careful, model-specific tuning for safe operation. We use reinforcement learning to train policies in simulation that transfer remarkably well to multiple different physical quadrotors. Our policies are low-level, i.e., we map the rotorcrafts' state directly to the motor outputs. The trained control policies are very robust to external disturbances and can withstand harsh initial conditions such as throws. We show how different training methodologies (change of the cost function, modeling of noise, use of domain randomization) might affect flight performance. To the best of our knowledge, this is the first work that demonstrates that a simple neural network can learn a robust stabilizing low-level quadrotor controller (without the use of a stabilizing PD controller) that is shown to generalize to multiple quadrotors.