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

Artem Molchanov, Tao Chen1, Wolfgang Hoenig2, James Preiss, Nora Ayanian1, Gaurav Sukhatme1

  • 1University of Southern California
  • 2California Institute of Technology

Details

11:30 - 11:45 | Tue 5 Nov | L1-R2 | TuAT2.3

Session: Deep Learning for Aerial Systems

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.