Non-parametric Auto-tuning Framework Using Modified Relay Feedback Test and Machine Learning for Multi-rotor UAVs

Thursday, June 3, 2021

System identification is a key discipline within the field of automation that deals with inferring mathematical models of dynamic systems based on input-output measurements. Conventional identification methods require extensive data generation and are thus not suitable for real-time applications. In this presentation, I will discuss a novel real-time approach for the parametric identification of linear systems using Deep Learning (DL) and the Modified Relay Feedback Test (MRFT) is proposed. The proposed approach requires only a single steady-state cycle of MRFT and guarantees stability and performance in the identification and control phases. The MRFT output is passed to a trained DL model that identifies the underlying process parameters in milliseconds. A novel modification to the Softmax function is derived to better conform the DL model for the process identification task. Quadrotor Unmanned Aerial Vehicle (UAV) attitude and altitude dynamics were used in simulation and experimentation to verify the presented approach. Results show the effectiveness and real-time capabilities of the proposed approach, which outperforms the conventional Prediction Error Method in terms of accuracy, robustness to biases, computational efficiency, and data requirements.

Watch now



Presenter Bio: Dr. Zweiri is currently an Associate Professor with Kingston University London in Kingston, U.K. He received his Ph.D. degree from King’s College London in 2003. He has been involved in defense and security research projects at Defense Science and Technology Laboratory (Dstl) at King’s College London, Field and Space Robotics Laboratory at the Massachusetts Institute of Technology (MIT), USA and King Abdullah II Design and Development Bureau (KADDB) in Jordan. Hid main research focus is interaction dynamics between unmanned systems and unknown environments by means of deep learning, machine intelligence, constrained optimization, and advanced control. Dr. Zweiri has published over 100 refereed journal and conference papers; and has filed five patents in USA and GB in the unmanned systems field. He has also served as the Associate Editor of ICRA2016 and IROS2019 conferences.