Loading [MathJax]/extensions/MathMenu.js
Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors | IEEE Conference Publication | IEEE Xplore

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


Abstract:

Quadrotor stabilizing controllers often require careful, model-specific tuning for safe operation. We use reinforcement learning to train policies in simulation that tran...Show More

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. The video of our experiments can be found at https://sites.google.com/view/sim-to-multi-quad.
Date of Conference: 03-08 November 2019
Date Added to IEEE Xplore: 28 January 2020
ISBN Information:

ISSN Information:

Conference Location: Macau, China

Contact IEEE to Subscribe

References

References is not available for this document.