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 - Afraj, Shahabaz A1 - Böhmländer, Dennis A1 - Vaculin, Ondrej A1 - Hynčík, Luděk T1 - Quantification methodology for crash behavior comparison between virtual crash simulations and real-time crash tests T2 - FISITA World Congress 2021 Y1 - 2021 UR - https://www.fisita.com/library/f2021-pif-072 PB - FISITA CY - Bishops Stortford 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 - 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 - CHAP A1 - Müller, Marcus A1 - Nadarajan, Parthasarathy A1 - Botsch, Michael A1 - Utschick, Wolfgang A1 - Böhmländer, Dennis A1 - Katzenbogen, Stefan T1 - A statistical learning approach for estimating the reliability of crash severity predictions T2 - 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC) UR - https://doi.org/10.1109/ITSC.2016.7795911 KW - vehicle crash testing KW - reliability KW - computer crashes KW - vehicles KW - mathematical model KW - accidents KW - predictive models Y1 - 2016 UR - https://doi.org/10.1109/ITSC.2016.7795911 SN - 978-1-5090-1889-5 SN - 2153-0017 SP - 2199 EP - 2206 PB - IEEE CY - Piscataway ER - TY - INPR A1 - Afraj, Shahabaz A1 - Vaculín, Ondřej A1 - Böhmländer, Dennis A1 - Hynčík, Luděk T1 - Vehicle Crash Simulation Models for Reinforcement Learning driven crash-detection algorithm calibration T2 - Research Square N2 - The development of finite element vehicle models for crash simulations is a highly complex task. The main aim of these models is to simulate a variety of crash scenarios and assess all the safety systems for their respective performances. These vehicle models possess a substantial amount of data pertaining to the vehicle's geometry, structure, materials, etc., and are used to estimate a large set of system and component level characteristics using crash simulations. It is understood that even the most well-developed simulation models are prone to deviations in estimation when compared to real-world physical test results. This is generally due to our inability to model the chaos and uncertainties introduced in the real world. Such unavoidable deviations render the use of virtual simulations ineffective for the calibration process of the algorithms that activate the restraint systems in the event of a crash (crash-detection algorithm). In the scope of this research, authors hypothesize the possibility of accounting for such variations introduced in the real world by creating a feedback loop between real-world crash tests and crash simulations. To accomplish this, a Reinforcement Learning (RL) compatible virtual surrogate model is used, which is adapted from crash simulation models. Hence, a conceptual methodology is illustrated in this paper for developing an RL-compatible model that can be trained using the results of crash simulations and crash tests. As the calibration of the crash-detection algorithm is fundamentally dependent upon the crash pulses, the scope of the expected output is limited to advancing the ability to estimate crash pulses. Furthermore, the real-time implementation of the methodology is illustrated using an actual vehicle model. UR - https://doi.org/10.21203/rs.3.rs-3004299/v1 KW - virtual vehicle models KW - crash tests KW - crash simulations KW - surrogate model KW - crash-detection algorithm KW - reinforcement Learning Y1 - 2023 UR - https://doi.org/10.21203/rs.3.rs-3004299/v1 SN - 2693-5015 PB - Research Square CY - Durham ER - TY - CHAP A1 - Böhmländer, Dennis A1 - Hasirlioglu, Sinan A1 - Yano, Vitor A1 - Lauerer, Christian A1 - Brandmeier, Thomas A1 - Zimmer, Alessandro T1 - Advantages in Crash Severity Prediction Using Vehicle to Vehicle Communication T2 - Proceedings: 2015 45th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops UR - https://doi.org/10.1109/DSN-W.2015.23 Y1 - 2015 UR - https://doi.org/10.1109/DSN-W.2015.23 SN - 978-1-4673-8044-7 SP - 112 EP - 117 PB - IEEE CY - Los Alamitos ER - TY - JOUR A1 - Böhmländer, Dennis A1 - Dirndorfer, Tobias A1 - Al-Bayatti, Ali H. A1 - Brandmeier, Thomas T1 - Context-aware system for pre-triggering irreversible vehicle safety actuators JF - Accident Analysis & Prevention UR - https://doi.org/10.1016/j.aap.2017.02.015 KW - Context-aware system KW - Driver behavior KW - Crash severity estimation KW - Collision mitigation KW - Pre-triggering KW - Vehicle safety Y1 - 2017 UR - https://doi.org/10.1016/j.aap.2017.02.015 SN - 1879-2057 VL - 2017 IS - 103 SP - 72 EP - 84 PB - Elsevier CY - Amsterdam ER -