TY - JOUR A1 - Flores Fernández, Alberto A1 - Wurst, Jonas A1 - Sánchez Morales, Eduardo A1 - Botsch, Michael A1 - Facchi, Christian A1 - García Higuera, Andrés T1 - Probabilistic Traffic Motion Labeling for Multi-Modal Vehicle Route Prediction JF - Sensors N2 - The prediction of the motion of traffic participants is a crucial aspect for the research and development of Automated Driving Systems (ADSs). Recent approaches are based on multi-modal motion prediction, which requires the assignment of a probability score to each of the multiple predicted motion hypotheses. However, there is a lack of ground truth for this probability score in the existing datasets. This implies that current Machine Learning (ML) models evaluate the multiple predictions by comparing them with the single real trajectory labeled in the dataset. In this work, a novel data-based method named Probabilistic Traffic Motion Labeling (PROMOTING) is introduced in order to (a) generate probable future routes and (b) estimate their probabilities. PROMOTING is presented with the focus on urban intersections. The generation of probable future routes is (a) based on a real traffic dataset and consists of two steps: first, a clustering of intersections with similar road topology, and second, a clustering of similar routes that are driven in each cluster from the first step. The estimation of the route probabilities is (b) based on a frequentist approach that considers how traffic participants will move in the future given their motion history. PROMOTING is evaluated with the publicly available Lyft database. The results show that PROMOTING is an appropriate approach to estimate the probabilities of the future motion of traffic participants in urban intersections. In this regard, PROMOTING can be used as a labeling approach for the generation of a labeled dataset that provides a probability score for probable future routes. Such a labeled dataset currently does not exist and would be highly valuable for ML approaches with the task of multi-modal motion prediction. The code is made open source. UR - https://doi.org/10.3390/s22124498 KW - PROMOTING KW - automated driving systems KW - autonomous vehicles KW - multi-modal KW - motion prediction KW - route prediction KW - machine learning KW - real traffic data Y1 - 2022 UR - https://doi.org/10.3390/s22124498 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-24341 SN - 1424-8220 VL - 22 IS - 12 PB - MDPI CY - Basel ER - TY - CHAP A1 - Chaulwar, Amit A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - A Hybrid Machine Learning Approach for Planning Safe Trajectories in Complex Traffic-Scenarios T2 - 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA) UR - https://doi.org/10.1109/ICMLA.2016.0095 KW - Hybrid learning algorithms KW - Trajectory Planning in Road Traffic KW - 3D-ConvNets Y1 - 2016 UR - https://doi.org/10.1109/ICMLA.2016.0095 SN - 978-1-5090-6167-9 SP - 540 EP - 546 PB - IEEE CY - Los Alamitos ER - TY - CHAP A1 - Chaulwar, Amit A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - A machine learning based biased-sampling approach for planning safe trajectories in complex, dynamic traffic-scenarios T2 - 2017 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IVS.2017.7995735 KW - Acceleration KW - Trajectory KW - Heuristic algorithms KW - Vehicle dynamics KW - Planning KW - Prediction algorithms KW - Roads Y1 - 2017 UR - https://doi.org/10.1109/IVS.2017.7995735 SN - 978-1-5090-4804-5 SP - 297 EP - 303 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Müller, Marcus A1 - Botsch, Michael A1 - Böhmländer, Dennis A1 - Utschick, Wolfgang ED - Klaffke, Werner T1 - A Simulation Framework for Vehicle Safety Testing T2 - Aktive Sicherheit und Automatisieres Fahren : 3. Interdisziplinärer Expertendialog (IEDAS) T2 - Ein Simulationsframework für die Absicherung von Fahrzeugsicherheitsfunktionen Y1 - 2017 SN - 978-3-8169-3405-9 SP - 147 EP - 167 PB - expert Verlag CY - Renningen ER - TY - JOUR A1 - Müller, Marcus A1 - Botsch, Michael A1 - Böhmländer, Dennis A1 - Utschick, Wolfgang T1 - Machine Learning Based Prediction of Crash Severity Distributions for Mitigation Strategies JF - Journal of Advances in Information Technology N2 - In road traffic, critical situations pass by as quickly as they appear. Within the blink of an eye, one has to come to a decision, which can make the difference between a low severity, high severity or fatal crash. Because time is important, a machine learning driven Crash Severity Predictor (CSP) is presented which provides the estimated crash severity distribution of an imminent crash in less than 0.2ms. This is 63⋅ 103 times faster compared to predicting the same distribution through computationally expensive numerical simulations. With the proposed method, even very complex crash data, like the results of Finite Element Method (FEM) simulations, can be made available ahead of a collision. Knowledge, which can be used to prepare occupants and vehicle to an imminent crash, activate and adjust safety measures like airbags or belt tensioners before of a collision or let self-driving vehicles go for the maneuver with the lowest crash severity. Using a real-world crash test it is shown that significant safety potential is left unused if instead of the CSP-proposed driving maneuver, no or the wrong actions are taken. UR - https://doi.org/10.12720/jait.9.1.15-24 KW - crash severity KW - vehicle safety KW - reliable prediction KW - machine learning Y1 - 2018 UR - https://doi.org/10.12720/jait.9.1.15-24 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-24644 SN - 1798-2340 VL - 9 (2018) IS - 1 SP - 15 EP - 24 PB - Engineering and Technology Publishing CY - Rowland Heights (CA) ER - TY - CHAP A1 - Cañas, Valentin A1 - Sánchez Morales, Eduardo A1 - Botsch, Michael A1 - García Higuera, Andres T1 - Wireless Communication System for the Validation of Autonomous Driving Functions on Full-Scale Vehicles T2 - 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES) UR - https://doi.org/10.1109/ICVES.2018.8519492 KW - Vehicle safety KW - wireless communication KW - autonomous driving KW - Intelligent Transport Systems Y1 - 2018 UR - https://doi.org/10.1109/ICVES.2018.8519492 SN - 978-1-5386-3543-8 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Chaulwar, Amit A1 - Botsch, Michael A1 - Utschick, Wolfgang ED - Kurková, Vera ED - Manolopoulos, Yannis ED - Hammer, Barbara ED - Iliadis, Lazaros ED - Maglogiannis, Ilias T1 - Generation of Reference Trajectories for Safe Trajectory Planning T2 - Artificial Neural Networks and Machine Learning – ICANN 2018 : 27th International Conference on Artificial Neural Networks,Rhodes, Greece, October 4–7, 2018 : Proceedings, Part I UR - https://doi.org/10.1007/978-3-030-01418-6_42 KW - Safe trajectory planning KW - Hybrid machine learning KW - Variational autoencoder Y1 - 2018 UR - https://doi.org/10.1007/978-3-030-01418-6_42 SN - 978-3-030-01418-6 SN - 978-3-030-01417-9 SP - 423 EP - 434 PB - Springer CY - Cham ER - TY - CHAP A1 - Gallitz, Oliver A1 - Botsch, Michael A1 - de Candido, Oliver A1 - Utschick, Wolfgang T1 - Validation of Machine Learning Algorithms through Visualization Methods T2 - ELIV-MarketPlace 2018 UR - https://doi.org/10.51202/9783181023389-29 Y1 - 2018 UR - https://doi.org/10.51202/9783181023389-29 SN - 978-3-18-092338-3 SN - 978-3-18-102338-9 SP - 29 EP - 46 PB - VDI Verlag CY - Düsseldorf ER - TY - CHAP A1 - Müller, Marcus A1 - Long, Xing A1 - Botsch, Michael A1 - Böhmländer, Dennis A1 - Utschick, Wolfgang T1 - Real-Time Crash Severity Estimation with Machine Learning and 2D Mass-Spring-Damper Model T2 - 2018 IEEE Intelligent Transportation Systems Conference UR - https://doi.org/10.1109/ITSC.2018.8569471 KW - computer crashes KW - vehicle crash testing KW - machine learning KW - two dimensional displays KW - forestry KW - accidents KW - acceleration Y1 - 2018 UR - https://doi.org/10.1109/ITSC.2018.8569471 SN - 978-1-7281-0323-5 SP - 2036 EP - 2043 PB - IEEE CY - Piscataway ER - TY - INPR A1 - Kruber, Friedrich A1 - Wurst, Jonas A1 - Botsch, Michael A1 - Chakraborty, Samarjit T1 - Highway traffic data: macroscopic, microscopic and criticality analysis for capturing relevant traffic scenarios and traffic modeling based on the highD data set UR - https://doi.org/10.48550/arXiv.1903.04249 KW - Time-To-Collision KW - Time-Headway KW - Risk Perception KW - traffic stream KW - traffic density KW - traffic flow rate KW - driver behavior KW - traffic simulation KW - highway traffic KW - highD Y1 - 2019 UR - https://doi.org/10.48550/arXiv.1903.04249 PB - arXiv CY - Ithaca ER -