Print Email Facebook Twitter End-to-end neural network based optimal quadcopter control Title End-to-end neural network based optimal quadcopter control Author Ferede, R. (TU Delft Control & Simulation) de Croon, G.C.H.E. (TU Delft Control & Simulation) de Wagter, C. (TU Delft Control & Simulation) Izzo, Dario (European Space Agency (ESA)) Date 2024 Abstract Developing optimal controllers for aggressive high-speed quadcopter flight poses significant challenges in robotics. Recent trends in the field involve utilizing neural network controllers trained through supervised or reinforcement learning. However, the sim-to-real transfer introduces a reality gap, requiring the use of robust inner loop controllers during real flights, which limits the network's control authority and flight performance. In this paper, we investigate for the first time, an end-to-end neural network controller, addressing the reality gap issue without being restricted by an inner-loop controller. The networks, referred to as G&CNets, are trained to learn an energy-optimal policy mapping the quadcopter's state to rpm commands using an optimal trajectory dataset. In hover-to-hover flights, we identified the unmodeled moments as a significant contributor to the reality gap. To mitigate this, we propose an adaptive control strategy that works by learning from optimal trajectories of a system affected by constant external pitch, roll and yaw moments. In real test flights, this model mismatch is estimated onboard and fed to the network to obtain the optimal rpm command. We demonstrate the effectiveness of our method by performing energy-optimal hover-to-hover flights with and without moment feedback. Finally, we compare the adaptive controller to a state-of-the-art differential-flatness-based controller in a consecutive waypoint flight and demonstrate the advantages of our method in terms of energy optimality and robustness. Subject End-to-end controlG&CNetOptimal controlReality gapSim-to-real transferSupervised learning To reference this document use: http://resolver.tudelft.nl/uuid:16169a19-bf6b-4681-8ecc-18a9f2bd5e0f DOI https://doi.org/10.1016/j.robot.2023.104588 ISSN 0921-8890 Source Robotics and Autonomous Systems, 172 Part of collection Institutional Repository Document type journal article Rights © 2024 R. Ferede, G.C.H.E. de Croon, C. de Wagter, Dario Izzo Files PDF 1_s2.0_S0921889023002270_main.pdf 4.58 MB Close viewer /islandora/object/uuid:16169a19-bf6b-4681-8ecc-18a9f2bd5e0f/datastream/OBJ/view