@article{FloresFernandezWurstSanchezMoralesetal.2022, author = {Flores Fern{\´a}ndez, Alberto and Wurst, Jonas and S{\´a}nchez Morales, Eduardo and Botsch, Michael and Facchi, Christian and Garc{\´i}a Higuera, Andr{\´e}s}, title = {Probabilistic Traffic Motion Labeling for Multi-Modal Vehicle Route Prediction}, volume = {22}, pages = {4498}, journal = {Sensors}, number = {12}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {https://doi.org/10.3390/s22124498}, year = {2022}, abstract = {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.}, language = {en} } @inproceedings{ChaulwarBotschUtschick2016, author = {Chaulwar, Amit and Botsch, Michael and Utschick, Wolfgang}, title = {A Hybrid Machine Learning Approach for Planning Safe Trajectories in Complex Traffic-Scenarios}, booktitle = {2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)}, publisher = {IEEE}, address = {Los Alamitos}, isbn = {978-1-5090-6167-9}, doi = {https://doi.org/10.1109/ICMLA.2016.0095}, pages = {540 -- 546}, year = {2016}, language = {en} } @inproceedings{ChaulwarBotschUtschick2017, author = {Chaulwar, Amit and Botsch, Michael and Utschick, Wolfgang}, title = {A machine learning based biased-sampling approach for planning safe trajectories in complex, dynamic traffic-scenarios}, booktitle = {2017 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-5090-4804-5}, doi = {https://doi.org/10.1109/IVS.2017.7995735}, pages = {297 -- 303}, year = {2017}, language = {en} } @inproceedings{MuellerBotschBoehmlaenderetal.2017, author = {M{\"u}ller, Marcus and Botsch, Michael and B{\"o}hml{\"a}nder, Dennis and Utschick, Wolfgang}, title = {A Simulation Framework for Vehicle Safety Testing}, booktitle = {Aktive Sicherheit und Automatisieres Fahren : 3. Interdisziplin{\"a}rer Expertendialog (IEDAS)}, editor = {Klaffke, Werner}, publisher = {expert Verlag}, address = {Renningen}, isbn = {978-3-8169-3405-9}, pages = {147 -- 167}, year = {2017}, language = {en} } @article{MuellerBotschBoehmlaenderetal.2018, author = {M{\"u}ller, Marcus and Botsch, Michael and B{\"o}hml{\"a}nder, Dennis and Utschick, Wolfgang}, title = {Machine Learning Based Prediction of Crash Severity Distributions for Mitigation Strategies}, volume = {9 (2018)}, journal = {Journal of Advances in Information Technology}, number = {1}, publisher = {Engineering and Technology Publishing}, address = {Rowland Heights (CA)}, issn = {1798-2340}, doi = {https://doi.org/10.12720/jait.9.1.15-24}, pages = {15 -- 24}, year = {2018}, abstract = {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.}, language = {en} } @inproceedings{CanasSanchezMoralesBotschetal.2018, author = {Ca{\~n}as, Valentin and S{\´a}nchez Morales, Eduardo and Botsch, Michael and Garc{\´i}a Higuera, Andres}, title = {Wireless Communication System for the Validation of Autonomous Driving Functions on Full-Scale Vehicles}, booktitle = {2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-5386-3543-8}, doi = {https://doi.org/10.1109/ICVES.2018.8519492}, year = {2018}, language = {en} } @inproceedings{ChaulwarBotschUtschick2018, author = {Chaulwar, Amit and Botsch, Michael and Utschick, Wolfgang}, title = {Generation of Reference Trajectories for Safe Trajectory Planning}, booktitle = {Artificial Neural Networks and Machine Learning - ICANN 2018 : 27th International Conference on Artificial Neural Networks,Rhodes, Greece, October 4-7, 2018 : Proceedings, Part I}, editor = {Kurkov{\´a}, Vera and Manolopoulos, Yannis and Hammer, Barbara and Iliadis, Lazaros and Maglogiannis, Ilias}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-01418-6}, doi = {https://doi.org/10.1007/978-3-030-01418-6_42}, pages = {423 -- 434}, year = {2018}, language = {en} } @inproceedings{GallitzBotschdeCandidoetal.2018, author = {Gallitz, Oliver and Botsch, Michael and de Candido, Oliver and Utschick, Wolfgang}, title = {Validation of Machine Learning Algorithms through Visualization Methods}, booktitle = {ELIV-MarketPlace 2018}, publisher = {VDI Verlag}, address = {D{\"u}sseldorf}, isbn = {978-3-18-092338-3}, doi = {https://doi.org/10.51202/9783181023389-29}, pages = {29 -- 46}, year = {2018}, language = {en} } @inproceedings{MuellerLongBotschetal.2018, author = {M{\"u}ller, Marcus and Long, Xing and Botsch, Michael and B{\"o}hml{\"a}nder, Dennis and Utschick, Wolfgang}, title = {Real-Time Crash Severity Estimation with Machine Learning and 2D Mass-Spring-Damper Model}, booktitle = {2018 IEEE Intelligent Transportation Systems Conference}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-7281-0323-5}, doi = {https://doi.org/10.1109/ITSC.2018.8569471}, pages = {2036 -- 2043}, year = {2018}, language = {en} } @unpublished{KruberWurstBotschetal.2019, author = {Kruber, Friedrich and Wurst, Jonas and Botsch, Michael and Chakraborty, Samarjit}, title = {Highway traffic data: macroscopic, microscopic and criticality analysis for capturing relevant traffic scenarios and traffic modeling based on the highD data set}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.1903.04249}, year = {2019}, language = {en} }