@inproceedings{7173, abstract = {Reinforcement learning has achieved state-of-the-art performance in MAV control, waypoint flight, and obstacle avoidance. However, existing RL approaches often assume fixed objectives and constraints, with flight behavior largely limited by vehicle dynamics and orientation considered only when required for locomotion. Classical planning and model predictive control handle such constraints explicitly, but require optimization or replanning. This motivates methods that combine learned local control with explicit constraint handling. We combine reinforcement learning with control barrier functions to improve constraint-aware execution. We propose parameterized waypoints that encode orientation, velocity, and corridor constraints. Simulation and real-world experiments show that a single policy can execute different constraint-parameterized navigation scenarios, revealing scenario-dependent trade-offs between traversal time, tracking accuracy, and constraint satisfaction.}, author = {Kirsch, André and Rexilius, Jan}, keywords = {MAV navigation, Reinforcement learning, Constrained navigation, Control barrier functions}, location = {Barcelona}, title = {{Reinforcement Learning-based MAV Navigation With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor Constraints}}, year = {2026}, } @inproceedings{7174, abstract = {This paper presents a hybrid control architecture for dynamic robotic picking tasks. The framework combines a Deep Reinforcement Learning policy for high-level interception with a dedicated Inverse Kinematics controller for precise terminal grasping, while mitigating precision limitations of monolithic learning-based approaches. The framework utilizes a Proximal Policy Optimization agent to approach moving targets, seamlessly transitioning to an Inverse Kinematics solver that reduces terminal orientational and positional errors while minimizing cumulative control effort. To facilitate deployment on physical hardware, a robust sim-to-real pipeline incorporating system identification, domain randomization, and latency injection is employed. Experimental results on a physical Franka Emika Panda manipulator validate this hybrid architecture. The system achieves an 80% success rate in pick-and-place tasks, compared to 60.8% for unadapted baselines, with no safety-critical violations such as joint limit breaches or collisions observed during testing.}, author = {Mayer, Patrick Thomas and Rexilius, Jan}, keywords = {Reinforcement Learning, Hybrid Control, Sim-to-Real, Robotic Manipulation, Inverse Kinematics.}, location = {Sapporo}, title = {{A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer}}, year = {2026}, } @inproceedings{7175, abstract = {Deep reinforcement learning (RL) policies for robotic control typically overfit to a single hardware configuration. Any change to the kinematic chain breaks the learned mapping and requires complete retraining. This paper investigates whether combining self-attention mechanisms with explicit spatial observations can improve a policy’s adaptability to varying kinematic topologies. We train a single RL agent to control a robotic manipulator across different degrees of freedom (DOF), ranging from a restricted 4-DOF mode to a fully redundant 7-DOF configuration. Instead of fixed-length state vectors, the method processes the active joints as a variable-length sequence in an attention buffer, enriching each joint’s representation with its relative spatial routing and geometric Jacobian influence. This structure allows the agent to dynamically evaluate the physical utility of its available actuators. The proposed Architecture reaches a success rate of 82.1% across trained topologies and 66.6% on unseen configurations, outperforming MLP and generic attention baselines while remaining nearly collisionfree. Finally, we demonstrate successful sim-to-real transfer by deploying the simulation-trained agent on a physical Franka Emika Panda manipulator.}, author = {Mayer, Patrick Thomas and Rexilius, Jan}, keywords = {Reinforcement Learning, Robotic Manipulation, Morphology Generalization, Sim-to-Real Transfer}, location = {Barcelona}, title = {{Adapting to Variable Kinematic Configurations: A Causal-Kinematic Attention Approach for Robotic Control}}, year = {2026}, } @inproceedings{6790, author = {Kirsch, André and Rexilius, Jan}, keywords = {Waste monitoring, Waste level estimation, MAV navigation}, location = {Lissabon, Portugal}, title = {{Vision-Based Autonomous Waste Bin Fill-Level Monitoring with a Micro Aerial Vehicle}}, doi = {10.1109/IE69249.2026.11539031}, year = {2026}, } @misc{6993, author = {Kirsch, André and Rexilius, Jan}, publisher = {Hochschule Bielefeld}, title = {{Waste Bin Dataset }}, year = {2026}, } @inproceedings{6982, author = {Riechmann-Thom, Malte and Rexilius, Jan}, booktitle = {IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)}, location = {Kitakyushu}, title = {{Multi-Perspective AR Interaction Through Robot Viewpoint Control}}, year = {2026}, } @inproceedings{6185, author = {Riechmann-Thom, Malte and Rexilius, Jan}, booktitle = {IEEE International Symposium on Mixed and Augmented Reality (ISMAR)}, location = {Daejeon, South Korea}, title = {{Visualizing Motion Intent in Heterogeneous Multi-Robot Environments}}, doi = {10.1109/ISMAR-Adjunct68609.2025.00145}, year = {2025}, } @inproceedings{6027, author = {Deutsch, Luis and König, Matthias and Rexilius, Jan}, booktitle = {KI-Kongress }, issn = {2943-3509}, location = {Bielefeld}, publisher = {Schriftenreihe des Institus for Data Science Solutions}, title = {{A State-Aware Ant Colony Optimization Approach to the Roll-on/Roll-off Problem for Skip Loaders}}, year = {2025}, } @inproceedings{6169, author = {Deutsch, Luis and König, Matthias and Rexilius, Jan}, booktitle = {Progress in IS , Advances in Environmental Informatics}, keywords = {Ant Colony Optimization, Vehicle Routing Problem, Rollon/ Roll-off, Skip Loader, Stackability}, location = {Potsdam}, publisher = {Springer}, title = {{An Adaptive Ant Colony System for Skip Loader Operations in Roll-on/Roll-off Logistics}}, year = {2025}, } @inproceedings{6186, author = {Riechmann-Thom, Malte and Rexilius, Jan}, booktitle = {ACM Symposium on Virtual Reality Software and Technology (VRST)}, location = {Montreal}, title = {{Interacting Beyond Reach: Multi-Perspective Augmented Reality for Precise Virtual Border Definition in Constrained Spaces}}, doi = {10.1145/3756884.3765993}, year = {2025}, } @misc{6764, author = {Blott, Gregor and Rexilius, Jan}, title = {{[EN] Method for determining video segments to be transferred}}, year = {2025}, } @inproceedings{5771, author = {Kirsch, André and Rexilius, Jan}, booktitle = { Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods }, editor = {Castrillon-Santana, Modesto and De Marsico, Maria and Fred, Ana }, isbn = { 978-989-758-730-6}, issn = {2184-4313}, keywords = {Tracking, Robot, Drone, MAV, External, Time-of-Flight, LiDAR}, location = {Porto}, publisher = {Science and Technology Publications}, title = {{ An Easy-to-Use System for Tracking Robotic Platforms Using Time-of-Flight Sensors in Lab Environments}}, doi = {10.5220/0013110500003905}, year = {2025}, } @misc{6747, author = {Blott, Gregor and Rexilius, Jan}, title = {{[EN] Surveillance system, method, computer programme, storage medium and surveillance device}}, year = {2024}, } @misc{6749, author = {Blott, Gregor and Rexilius, Jan and Roland, Matthias}, title = {{[EN] Anonymisation apparatus, monitoring device, method, computer program and storage medium}}, year = {2024}, } @misc{6762, author = {Blott, Gregor and Rexilius, Jan}, title = {{Monitoring device, monitoring system, method, computer program and machine-readable storage medium}}, year = {2024}, } @misc{6763, author = {Blott, Gregor and Rexilius, Jan}, title = {{Surveillance system, method, computer program, storage medium and surveillance device}}, year = {2024}, } @inproceedings{5281, author = {Riechmann-Thom, Malte and Kirsch, André and König, Matthias and Rexilius, Jan}, booktitle = {2024 IEEE International Conference on Robotics and Automation (ICRA)}, location = {Yokohama}, title = {{Virtual Borders in 3D: Defining a Drone’s Movement Space Using Augmented Reality}}, doi = {10.1109/ICRA57147.2024.10610259}, year = {2024}, } @misc{5269, author = {Kirsch, André and Rexilius, Jan}, publisher = {Hochschule Bielefeld}, title = {{Robotic Platform Tracking}}, year = {2024}, } @inproceedings{2292, author = {Viertel, Philipp and König, Matthias and Rexilius, Jan}, booktitle = {Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM}, editor = {De Marsico, Maria and Sanniti di Baja, Gabriella and Fred , Ana}, isbn = {978-989-758-626-2}, location = {Lisbon, Portugal}, pages = {418--425}, title = {{Metric-Based Few-Shot Learning for Pollen Grain Image Classification}}, doi = {10.5220/0011727900003411}, year = {2023}, } @misc{6735, author = {Blott, Gregor and Rexilius, Jan}, title = {{[DE] Verfahren zum Bestimmen von zu übertragenden Videoabschnitten }}, year = {2023}, }