In recent years there has been an exploding interest in extending the current applications of multirotor UAVs to those that require aerial physical interaction, such as contact-based inspection, aerial writing, and tool handling on hard-to-reach surfaces. Impedance control is a widely used interaction-control technique for aerial and ground robots. To achieve consistent performance during impedance control tasks, an a-priori knowledge of the environment parameters is needed to adjust the controller’s impedance parameters accordingly.
For the task of aerial writing on unknown surfaces, this unknown knowledge of the environment makes it challenging to achieve a consistent outcome for the interaction task. In this thesis, a framework based on Bayesian Optimization (BO) is used to find the optimum parameters of an impedance-controlled aerial robot. Since BO is an iterative method, a reward function describing the performances of the writings of the aerial robot on unknown flat surfaces was proposed. Using the techniques of Sim2Real transfer learning such as domain randomization, several unique simulation scenarios were created. BO was used to find the optimal controller parameters for every simulation which are to be utilized later in the training of neural networks.