@article{Pfaff2023,
  author    = {Pfaff, Raphael},
  title     = {Braking distance prediction for vehicle consist in low-speed on-sight operation: a Monte Carlo approach},
  series = {Railway Engineering Science},
  volume    = {31},
  journal   = {Railway Engineering Science},
  number    = {2},
  publisher = {SpringerOpen},
  issn      = {2662-4753 (eISSN)},
  doi       = {10.1007/s40534-023-00303-7},
  pages     = {135 -- 144},
  year      = {2023},
  abstract  = {The first and last mile of a railway journey, in both freight and transit applications, constitutes a high effort and is either non-productive (e.g. in the case of depot operations) or highly inefficient (e.g. in industrial railways). These parts are typically managed on-sight, i.e. with no signalling and train protection systems ensuring the freedom of movement. This is possible due to the rather short braking distances of individual vehicles and shunting consists. The present article analyses the braking behaviour of such shunting units. For this purpose, a dedicated model is developed. It is calibrated on published results of brake tests and validated against a high-definition model for low-speed applications. Based on this model, multiple simulations are executed to obtain a Monte Carlo simulation of the resulting braking distances. Based on the distribution properties and established safety levels, the risk of exceeding certain braking distances is evaluated and maximum braking distances are derived. Together with certain parameters of the system, these can serve in the design and safety assessment of driver assistance systems and automation of these processes.},
  language  = {en}
}
@article{ThomessenThomaBraun2023,
  author    = {Thomessen, Karolin and Thoma, Andreas and Braun, Carsten},
  title     = {Bio-inspired altitude changing extension to the 3DVFH* local obstacle avoidance algorithm},
  series = {CEAS Aeronautical Journal},
  journal   = {CEAS Aeronautical Journal},
  publisher = {Springer},
  address   = {Wien},
  issn      = {1869-5590 (Online)},
  doi       = {10.1007/s13272-023-00691-w},
  pages     = {11 Seiten},
  year      = {2023},
  abstract  = {Obstacle avoidance is critical for unmanned aerial vehicles (UAVs) operating autonomously. Obstacle avoidance algorithms either rely on global environment data or local sensor data. Local path planners react to unforeseen objects and plan purely on local sensor information. Similarly, animals need to find feasible paths based on local information about their surroundings. Therefore, their behavior is a valuable source of inspiration for path planning. Bumblebees tend to fly vertically over far-away obstacles and horizontally around close ones, implying two zones for different flight strategies depending on the distance to obstacles. This work enhances the local path planner 3DVFH* with this bio-inspired strategy. The algorithm alters the goal-driven function of the 3DVFH* to climb-preferring if obstacles are far away. Prior experiments with bumblebees led to two definitions of flight zone limits depending on the distance to obstacles, leading to two algorithm variants. Both variants reduce the probability of not reaching the goal of a 3DVFH* implementation in Matlab/Simulink. The best variant, 3DVFH*b-b, reduces this probability from 70.7 to 18.6\% in city-like worlds using a strong vertical evasion strategy. Energy consumption is higher, and flight paths are longer compared to the algorithm version with pronounced horizontal evasion tendency. A parameter study analyzes the effect of different weighting factors in the cost function. The best parameter combination shows a failure probability of 6.9\% in city-like worlds and reduces energy consumption by 28\%. Our findings demonstrate the potential of bio-inspired approaches for improving the performance of local path planning algorithms for UAV.},
  language  = {en}
}
@inproceedings{AltherrConzenElsenetal.2023,
  author    = {Altherr, Lena and Conzen, Max and Elsen, Ingo and Frauenrath, Tobias and Lyrmann, Andreas},
  title     = {Sensor retrofitting of existing buildings in an interdisciplinary teaching project at university level},
  series = {Tagungsband AALE 2023 : mit Automatisierung gegen den Klimawandel},
  booktitle = {Tagungsband AALE 2023 : mit Automatisierung gegen den Klimawandel},
  editor    = {Reiff-Stephan, J{\"o}rg and J{\"a}kel, Jens and Schwarz, Andr{\´e}},
  publisher = {le-tex publishing services GmbH},
  address   = {Leipzig},
  isbn      = {978-3-910103-01-6},
  doi       = {10.33968/2023.04},
  pages     = {31 -- 40},
  year      = {2023},
  abstract  = {Existing residential buildings have an average lifetime of 100 years. Many of these buildings will exist for at least another 50 years. To increase the efficiency of these buildings while keeping costs at reasonable rates, they can be retrofitted with sensors that deliver information to central control units for heating, ventilation and electricity. This retrofitting process should happen with minimal intervention into existing infrastructure and requires new approaches for sensor design and data transmission. At FH Aachen University of Applied Sciences, students of different disciplines work together to learn how to design, build, deploy and operate such sensors. The presented teaching project already created a low power design for a combined CO2, temperature and humidity measurement device that can be easily integrated into most home automation systems},
  language  = {en}
}
@article{UlmerBraunChengetal.2023,
  author    = {Ulmer, Jessica and Braun, Carsten and Cheng, Chi-Tsun and Dowey, Steve and Wollert, J{\"o}rg},
  title     = {A human factors-aware assistance system in manufacturing based on gamification and hardware modularisation},
  series = {International Journal of Production Research},
  journal   = {International Journal of Production Research},
  publisher = {Taylor \& Francis},
  issn      = {0020-7543 (Print)},
  doi       = {10.1080/00207543.2023.2166140},
  year      = {2023},
  abstract  = {Assistance systems have been widely adopted in the manufacturing sector to facilitate various processes and tasks in production environments. However, existing systems are mostly equipped with rigid functional logic and do not provide individual user experiences or adapt to their capabilities. This work integrates human factors in assistance systems by adjusting the hardware and instruction presented to the workers' cognitive and physical demands. A modular system architecture is designed accordingly, which allows a flexible component exchange according to the user and the work task. Gamification, the use of game elements in non-gaming contexts, has been further adopted in this work to provide level-based instructions and personalised feedback. The developed framework is validated by applying it to a manual workstation for industrial assembly routines.},
  language  = {en}
}
@inproceedings{ThomaStiemerBraunetal.2023,
  author    = {Thoma, Andreas and Stiemer, Luc and Braun, Carsten and Fisher, Alex and Gardi, Alessandro G.},
  title     = {Potential of hybrid neural network local path planner for small UAV in urban environments},
  series = {AIAA SCITECH 2023 Forum},
  booktitle = {AIAA SCITECH 2023 Forum},
  publisher = {AIAA},
  doi       = {10.2514/6.2023-2359},
  pages     = {13 Seiten},
  year      = {2023},
  abstract  = {This work proposes a hybrid algorithm combining an Artificial Neural Network (ANN) with a conventional local path planner to navigate UAVs efficiently in various unknown urban environments. The proposed method of a Hybrid Artificial Neural Network Avoidance System is called HANNAS. The ANN analyses a video stream and classifies the current environment. This information about the current Environment is used to set several control parameters of a conventional local path planner, the 3DVFH*. The local path planner then plans the path toward a specific goal point based on distance data from a depth camera. We trained and tested a state-of-the-art image segmentation algorithm, PP-LiteSeg. The proposed HANNAS method reaches a failure probability of 17\%, which is less than half the failure probability of the baseline and around half the failure probability of an improved, bio-inspired version of the 3DVFH*. The proposed HANNAS method does not show any disadvantages regarding flight time or flight distance.},
  language  = {en}
}
@article{StiemerThomaBraun2023,
  author    = {Stiemer, Luc Nicolas and Thoma, Andreas and Braun, Carsten},
  title     = {MBT3D: Deep learning based multi-object tracker for bumblebee 3D flight path estimation},
  series = {PLoS ONE},
  volume    = {18},
  journal   = {PLoS ONE},
  number    = {9},
  publisher = {PLOS},
  address   = {San Fancisco},
  issn      = {1932-6203},
  doi       = {10.1371/journal.pone.0291415},
  pages     = {e0291415},
  year      = {2023},
  abstract  = {This work presents the Multi-Bees-Tracker (MBT3D) algorithm, a Python framework implementing a deep association tracker for Tracking-By-Detection, to address the challenging task of tracking flight paths of bumblebees in a social group. While tracking algorithms for bumblebees exist, they often come with intensive restrictions, such as the need for sufficient lighting, high contrast between the animal and background, absence of occlusion, significant user input, etc. Tracking flight paths of bumblebees in a social group is challenging. They suddenly adjust movements and change their appearance during different wing beat states while exhibiting significant similarities in their individual appearance. The MBT3D tracker, developed in this research, is an adaptation of an existing ant tracking algorithm for bumblebee tracking. It incorporates an offline trained appearance descriptor along with a Kalman Filter for appearance and motion matching. Different detector architectures for upstream detections (You Only Look Once (YOLOv5), Faster Region Proposal Convolutional Neural Network (Faster R-CNN), and RetinaNet) are investigated in a comparative study to optimize performance. The detection models were trained on a dataset containing 11359 labeled bumblebee images. YOLOv5 reaches an Average Precision of AP = 53, 8\%, Faster R-CNN achieves AP = 45, 3\% and RetinaNet AP = 38, 4\% on the bumblebee validation dataset, which consists of 1323 labeled bumblebee images. The tracker's appearance model is trained on 144 samples. The tracker (with Faster R-CNN detections) reaches a Multiple Object Tracking Accuracy MOTA = 93, 5\% and a Multiple Object Tracking Precision MOTP = 75, 6\% on a validation dataset containing 2000 images, competing with state-of-the-art computer vision methods. The framework allows reliable tracking of different bumblebees in the same video stream with rarely occurring identity switches (IDS). MBT3D has much lower IDS than other commonly used algorithms, with one of the lowest false positive rates, competing with state-of-the-art animal tracking algorithms. The developed framework reconstructs the 3-dimensional (3D) flight paths of the bumblebees by triangulation. It also handles and compares two alternative stereo camera pairs if desired.},
  language  = {en}
}