Learning to Fly
Neural Lander: Stable Drone Landing Control using Learned Dynamics
Guanya Shi, Xichen Shi, Michael O'Connell, Rose Yu, Kamyar Azizzadenesheli, Animashree Anandkumar, Yisong Yue, Soon-Jo Chung
submitted to International Conference on Robotics and Automation (ICRA), 2019
We present a novel deep-learning-based robust nonlinear controller for stable quadrotor control during landing. Our approach blends together a nominal dynamics model coupled with a DNN that learns the high-order interactions, such as the complex interactions between the ground and multi-rotor airflow. To the best of our knowledge, this is the first DNN-based nonlinear feedback controller with stability guarantees that can utilize arbitrarily large neural nets. [Video]
Some relevant papers
S. Rahili, B. Riviere, S. Oliver, and S.-J. Chung, "Optimal Routing for Autonomous Taxis and Ridesharing: Distributed Reinforcement Learning Approach," IEEE ICDM 2018 Workshops Proc. of 1st Workshop on Data-driven Intelligent Transportation (DIT 2018), Singapore, 17 November 2018.