TY - CHAP A1 - Ammalladene-Venkata, Manogna A1 - Seidel, Christian A1 - Halbe, Omkar A1 - Groitl, Christine A1 - Stahl, Christoph T1 - Deep Learning Based Obstacle Awareness from Airborne Optical Sensors T2 - 77th Annual Vertical Flight Society Forum and Technology Display (FORUM 77), the Future of Vertical Flight UR - https://doi.org/10.4050/F-0077-2021-16905 KW - Deep learning KW - Airborne Sensors KW - Obstacle Awareness Y1 - 2021 UR - https://doi.org/10.4050/F-0077-2021-16905 SN - 978-1-7138-3001-6 PB - Vertical Flight Society CY - Fairfax ER - TY - JOUR A1 - Ammalladene-Venkata, Manogna A1 - Halbe, Omkar A1 - Seidel, Christian A1 - Groitl, Christine A1 - Kramel, Lothar A1 - Stahl, Christoph A1 - Seidel, Heiko T1 - Deep Learning Based Obstacle Awareness from Airborne Optical Sensors JF - Journal of the American Helicopter Society N2 - Aviation statistics identify collision with terrain and obstacles as a leading cause of helicopter accidents. Assisting helicopter pilots in detecting the presence of obstacles can greatly mitigate the risk of collisions. However, only a limited number of helicopters in operation have an installed helicopter terrain awareness and warning system (HTAWS), while the cost of active obstacle warning systems remains prohibitive for many civil operators. In this work, we apply machine learning to automate obstacle detection and classification in combination with commercially available airborne optical sensors. While numerous techniques for learning-based object detection have been published in the literature, many of them are data and computation intensive. Our approach seeks to balance the detection and classification accuracy of the method with the size of the training data required and the runtime. Specifically, our approach combines the invariant feature extraction ability of pretrained deep convolutional neural networks (CNNs) and the high-speed training and classification ability of a novel, proprietary frequency-domain support vector machine (SVM) method. We describe our experimental setup comprising the CNN + SVM model and datasets of predefined classes of obstacles—pylons, chimneys, antennas, TV towers, wind turbines, helicopters—synthesized from prerecorded airborne video sequences of low-altitude helicopter flight. We analyze the detection performance using average precision, average recall, and runtime performance metrics on representative test data. Finally, we present a simple architecture for real-time, onboard implementation and discuss the obstacle detection performance of recently concluded flight tests. UR - https://doi.org/10.4050/JAHS.68.042012 Y1 - 2023 UR - https://doi.org/10.4050/JAHS.68.042012 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-43350 SN - 2161-6027 SN - 0002-8711 VL - 68 IS - 4 SP - 42012 EP - 42024 PB - Vertical Flight Society CY - Fairfax ER - TY - CHAP A1 - Seidel, Christian A1 - Schwartz, Ingo A1 - Kielhorn, Peter ED - Kamerman, Gary W. ED - Steinvall, Ove K. ED - Lewis, Keith L. ED - Merlet, Thomas J. ED - Hollins, Richard C. T1 - Helicopter collision avoidance and brown-out recovery with HELLAS T2 - Electro-Optical Remote Sensing, Photonic Technologies, and Applications II UR - https://doi.org/10.1117/12.800180 Y1 - 2008 UR - https://doi.org/10.1117/12.800180 SN - 978-0-8194-7346-2 PB - SPIE CY - Bellingham ER - TY - CHAP A1 - Seidel, Christian A1 - Samuelis, Christian A1 - Wegner, Matthias A1 - Münsterer, Thomas A1 - Rumpf, Thomas A1 - Schwartz, Ingo ED - Kamerman, Gary W. ED - Turner, Monte D. T1 - Novel approaches to helicopter obstacle warning T2 - Laser Radar Technology and Applications XI UR - https://doi.org/10.1117/12.664042 Y1 - 2006 UR - https://doi.org/10.1117/12.664042 SN - 978-0-8194-6270-1 PB - SPIE CY - Bellingham ER - TY - CHAP A1 - Seidel, Christian A1 - Trommer, Gert F. ED - Righini, Giancarlo C. ED - Honkanen, Seppo T1 - Modeling of bias errors in fiber optic gyroscopes with new simulation tool T2 - Integrated Optics and Photonic Integrated Circuits UR - https://doi.org/10.1117/12.544087 Y1 - 2004 UR - https://doi.org/10.1117/12.544087 SN - 978-0-8194-5374-7 PB - SPIE CY - Bellingham ER - TY - JOUR A1 - Seidel, Christian A1 - Trommer, Gert F. T1 - Modelling of Fibre-Optic Gyroscopes with Low-Coherence Light Sources JF - International Journal of Modelling and Simulation UR - https://doi.org/10.1080/02286203.2005.11442320 Y1 - 2005 UR - https://doi.org/10.1080/02286203.2005.11442320 SN - 0228-6203 SN - 1925-7082 VL - 25 IS - 2 SP - 71 EP - 78 PB - Taylor & Francis CY - London ER - TY - CHAP A1 - Seidel, Christian A1 - Trommer, Gert F. ED - Lopez-Higuera, Jose Miguel ED - Culshaw, Brian T1 - Measurement of nonlinear effects in fiber optic gyroscopes with different light sources T2 - Second European Workshop on Optical Fibre Sensors UR - https://doi.org/10.1117/12.566720 Y1 - 2004 UR - https://doi.org/10.1117/12.566720 SN - 978-0-8194-5434-8 PB - SPIE CY - Bellingham ER - TY - CHAP A1 - Seidel, Christian A1 - Trommer, Gert F. ED - Sorg, Helmut T1 - Bias Errors in Fiber-Optic Gyroscopes Caused by Lyot Depolarizers T2 - Symposium Gyro Technology 2004, Stuttgart, Germany, September 21/22, 2004 Y1 - 2004 SP - 8.0 EP - 8.12 PB - Universität Stuttgart CY - Stuttgart ER - TY - JOUR A1 - Salamat, Babak A1 - Bencic, Daniel A1 - Elsbacher, Gerhard A1 - Seidel, Christian A1 - Tonello, Andrea M. T1 - Investigating Integral Reinforcement Learning to Achieve Asymptotic Stability in Underactuated Mechanical Systems JF - IEEE Robotics and Automation Letters UR - https://doi.org/10.1109/LRA.2023.3332556 Y1 - 2023 UR - https://doi.org/10.1109/LRA.2023.3332556 SN - 2377-3766 VL - 9 IS - 1 SP - 191 EP - 198 PB - IEEE CY - New York ER - TY - INPR A1 - Salamat, Babak A1 - Mattern, Dominik A1 - Olzem, Sebastian-Sven A1 - Elsbacher, Gerhard A1 - Seidel, Christian A1 - Tonello, Andrea M. T1 - GMP3: Learning-Driven, Bellman-Guided Trajectory Planning for UAVs in Real-Time on SE(3) N2 - We propose GMP3, a multiphase global path planning framework that generates dynamically feasible three-dimensional trajectories for unmanned aerial vehicles (UAVs) operating in cluttered environments. The framework extends traditional path planning from Euclidean position spaces to the Lie group SE(3), allowing joint learning of translational motion and rotational dynamics. A modified Bellman-based operator is introduced to support reinforcement learning (RL) policy updates while leveraging prior trajectory information for improved convergence. GMP3 is designed as a distributed framework in which agents influence each other and share policy information along the trajectory: each agent refines its assigned segment and shares with its neighbors via a consensus-based scheme, enabling cooperative policy updates and convergence toward a path shaped globally even under kinematic constraints. We also propose DroneManager, a modular ground control software that interfaces the planner with real UAV platforms via the MAVLink protocol, supporting real-time deployment and feedback. Simulation studies and indoor flight experiments validate the effectiveness of the proposed method in constrained 3D environments, demonstrating reliable obstacle avoidance and smooth, feasible trajectories across both position and orientation. The open-source implementation is available at https://github.com/Domattee/DroneManager. UR - https://doi.org/10.48550/arXiv.2509.21264 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2509.21264 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-64770 PB - arXiv CY - Ithaca ER - TY - JOUR A1 - Salamat, Babak A1 - Mattern, Dominik A1 - Olzem, Sebastian-Sven A1 - Elsbacher, Gerhard A1 - Seidel, Christian A1 - Tonello, Andrea M. T1 - GMP3: Learning-Driven, Bellman-Guided Trajectory Planning for AAVs in Real-Time on SE(3) JF - IEEE Access N2 - We propose GMP3, a multiphase global path planning framework that generates dynamically feasible three-dimensional trajectories for unmanned aerial vehicles (UAVs) operating in cluttered environments. The framework extends traditional path planning from Euclidean position spaces to the Lie group SE(3), allowing joint learning of translational motion and rotational dynamics. A modified Bellman-based operator is introduced to support reinforcement learning (RL) policy updates while leveraging prior trajectory information for improved convergence. GMP3 is designed as a distributed framework in which agents influence each other and share policy information along the trajectory: each agent refines its assigned segment and shares with its neighbors via a consensus-based scheme, enabling cooperative policy updates and convergence toward a path shaped globally even under kinematic constraints.We also propose DroneManager, a modular ground control software that interfaces the planner with real UAVs platforms via the Micro Air Vehicle Link (MAVLink) protocol, supporting real-time deployment and feedback. Simulation studies and indoor flight experiments validate the effectiveness of the proposed method in constrained 3D environments, demonstrating reliable obstacle avoidance and smooth, feasible trajectories across both position and orientation. UR - https://doi.org/10.1109/ACCESS.2026.3661193 Y1 - 2026 UR - https://doi.org/10.1109/ACCESS.2026.3661193 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-66826 SN - 2169-3536 VL - 14 SP - 22720 EP - 22733 PB - IEEE CY - New York ER -