학술논문
Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors
Document Type
Conference
Author
Source
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Intelligent Robots and Systems (IROS), 2019 IEEE/RSJ International Conference on. :59-66 Nov, 2019
Subject
Language
ISSN
2153-0866
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.