Differential Dynamic Programming for Aerial Robots using an Aerodynamics Model

Abstract

State of the art trajectory generation schemes for quadrotors assume a simple dynamic model. They neglect aerodynamic effects such as induced drag and blade flapping and assume that no wind is present. In order to overcome this limitation, this thesis investigates a trajectory optimization scheme based upon Differential Dynamic Programming (DDP). There are various software-implementations of the DDP scheme. For future deployment on robotic hardware the software is required to be computationally efficient and to be open-source. The C++ template-based optimization library named GCOP developed at JHU was deemed suitable so it was selected for this purpose. Before implementing the solver, a full model of the Crazyflie Nano Quadcopter is identified experimentally. The model considers a first order term for the aerodynamic forces in each axis of the body frame. The solver is validated, normalized and the performance is benchmarked. This method yields reliable minimum control-effort trajectories. The computation time required to reach the optimum solution is studied for different dicretizations, and for different choices of solver parameters. A control scheme is proposed and studied in Monte-Carlo simulations. It is robust and able to handle large modelling errors in mass and moment of inertia while ensuring minimal error on the final state.