Control of a Quadrotor With Reinforcement Learning

In this letter, we present a method to control a quadrotor with a neural network trained using reinforcement learning techniques. With reinforcement learning, a common network can be trained to directly map state to actuator command making any predefined control structure obsolete for training. Moreover, we present a new learning algorithm that differs from the existing ones in certain aspects. Our algorithm is conservative but stable for complicated tasks. We found that it is more applicable to controlling a quadrotor than existing algorithms. We demonstrate the performance of the trained policy both in simulation and with a real quadrotor. Experiments show that our policy network can react to step response…

• SN
  Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
• NC
  National Centre of Competence in Research Robotics

  Award: 200021-166232