06 Fakultät Luft- und Raumfahrttechnik und Geodäsie

Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/7

Browse

Publication Type: search.filters.UBSTyp.ZeitschriftenartikelInstitute: search.filters.UBSInstitut.Institut für Flugmechanik und FlugregelungStart date: 2024

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Reinforcement learning based autonomous multi-rotor landing on moving platforms
    (2024) Goldschmid, Pascal; Ahmad, Aamir
    Multi-rotor UAVs suffer from a restricted range and flight duration due to limited battery capacity. Autonomous landing on a 2D moving platform offers the possibility to replenish batteries and offload data, thus increasing the utility of the vehicle. Classical approaches rely on accurate, complex and difficult-to-derive models of the vehicle and the environment. Reinforcement learning (RL) provides an attractive alternative due to its ability to learn a suitable control policy exclusively from data during a training procedure. However, current methods require several hours to train, have limited success rates and depend on hyperparameters that need to be tuned by trial-and-error. We address all these issues in this work. First, we decompose the landing procedure into a sequence of simpler, but similar learning tasks. This is enabled by applying two instances of the same RL based controller trained for 1D motion for controlling the multi-rotor’s movement in both the longitudinal and the lateral directions. Second, we introduce a powerful state space discretization technique that is based on i) kinematic modeling of the moving platform to derive information about the state space topology and ii) structuring the training as a sequential curriculum using transfer learning. Third, we leverage the kinematics model of the moving platform to also derive interpretable hyperparameters for the training process that ensure sufficient maneuverability of the multi-rotor vehicle. The training is performed using the tabular RL method Double Q-Learning . Through extensive simulations we show that the presented method significantly increases the rate of successful landings, while requiring less training time compared to other deep RL approaches. Furthermore, for two comparison scenarios it achieves comparable performance than a cascaded PI controller. Finally, we deploy and demonstrate our algorithm on real hardware. For all evaluation scenarios we provide statistics on the agent’s performance. Source code is openly available at https://github.com/robot-perception-group/rl_multi_rotor_landing .
  • Thumbnail Image
    ItemOpen Access
    Decomposed quasiconvex optimization with application to generalized cone problems
    (2024) Cunis, Torbjørn
    We propose a gradient-based method to solve quasiconvex optimization problems through decomposed optimization and prove local superlinear convergence under mild regularity assumptions at the optimal solution. A practical implementation further provides global convergence while maintaining the fast local convergence. In numerical examples from generalized cone programming, the proposed method reduced the number of iterations to 18 to 50% compared to bisection.
  • Thumbnail Image
    ItemOpen Access
    Adapting e-Genius for next-level efficient electric aerotow with high-power propulsion and automatic flight control system
    (2025) Zistler, Stefan; Shi, Dalong; Fichter, Walter; Strohmayer, Andreas
    Aiming to reduce energy demand and carbon footprint, minimize noise impact, and enhance flight safety and efficiency during aerotow operations, this study integrates an electric propulsion system and an automatic flight control system (AFCS) into the electric research aircraft e-Genius. An advanced propulsion system is developed using high-performance batteries and available electric drive components, while the AFCS is designed following a systematic process of developing flight control algorithms. Flight tests are then conducted to evaluate the performance of individual components and the overall system. The test results demonstrate that the upgraded propulsion system provides sufficient power to launch sailplanes, even with the maximum takeoff mass, while significantly reducing energy demand when compared to contemporary fossil fueled towplanes. Additionally, the AFCS proves to be stable and robust, successfully following specified commanded states, executing path tracking, and performing aerotow operations.