001052307 001__ 1052307
001052307 005__ 20260122220308.0
001052307 037__ $$aFZJ-2026-00918
001052307 088__ $$2Other$$aWhitepaper 1
001052307 1001_ $$0P:(DE-Juel1)180916$$aAach, Marcel$$b0$$ufzj
001052307 245__ $$aAutomotive Foundation Models: Fundamentals, Training Concepts and Applications
001052307 260__ $$c2025
001052307 300__ $$a177 p.
001052307 3367_ $$2DRIVER$$areport
001052307 3367_ $$2ORCID$$aREPORT
001052307 3367_ $$010$$2EndNote$$aReport
001052307 3367_ $$2DataCite$$aOutput Types/Report
001052307 3367_ $$0PUB:(DE-HGF)29$$2PUB:(DE-HGF)$$aReport$$breport$$mreport$$s1769095269_32683
001052307 3367_ $$2BibTeX$$aTECHREPORT
001052307 520__ $$aGenerative AI has gained wide attention through large-scale models such as DALL-E 3, StableDiffusion, and GPT-4, creating new opportunities for innovation while raising important ethicalquestions. At the core of these advancements are foundation models: massive neural networkspretrained on extensive datasets and designed to adapt across diverse tasks and data modalities.Their ability to unify camera, LiDAR, radar, and other sensor data has significant potential forenhancing perception, prediction, and planning in autonomous driving. <br>This report discusses the fundamental concepts underlying foundation models, including theirarchitectural structures, training regimens, and interpretability considerations. It examines cur-rent literature for foundation models and their application and use in the domain of autonomousdriving. Techniques for generative sensor data synthesis are outlined, demonstrating how arti-ficial datasets can replicate complex driving environments and reduce the expense of collectingreal-world samples. Methods for extending these generative approaches to sequential or videodata are also highlighted, enabling realistic motion forecasting and scenario simulation. Fi-nally, the report explores how abstract representations, such as semantic maps or symbolic data,can increase explainability and computational efficiency when applied to autonomous driving.This whitepaper aims to provide both foundational understanding and practical guidance ofthe current state-of-the-art for leveraging generative AI and foundation models in the field ofautonomous driving.
001052307 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001052307 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x1
001052307 536__ $$0G:(BMWK)19A23014l$$anxtAIM - nxtAIM – NXT GEN AI Methods (19A23014l)$$c19A23014l$$x2
001052307 536__ $$0G:(DE-Juel-1)SDLFSE$$aSDL Fluids & Solids Engineering$$cSDLFSE$$x3
001052307 7001_ $$0P:(DE-HGF)0$$aAdolph, Laurenz$$b1
001052307 7001_ $$0P:(DE-HGF)0$$aBaumann, Stefan$$b2
001052307 7001_ $$0P:(DE-Juel1)192312$$aBenassou, Sabrina$$b3$$ufzj
001052307 7001_ $$0P:(DE-HGF)0$$aBernhard, David$$b4
001052307 7001_ $$0P:(DE-HGF)0$$aBernhard, Sebastian$$b5
001052307 7001_ $$0P:(DE-HGF)0$$aBouzidi, Mohamed-Khalil$$b6
001052307 7001_ $$0P:(DE-HGF)0$$aBraun, Markus$$b7
001052307 7001_ $$0P:(DE-HGF)0$$aBrox, Thomas$$b8
001052307 7001_ $$0P:(DE-HGF)0$$aBurdorf, Sven$$b9
001052307 7001_ $$0P:(DE-HGF)0$$aDauner, Daniel$$b10
001052307 7001_ $$0P:(DE-HGF)0$$aGraaff, Thies de$$b11
001052307 7001_ $$0P:(DE-HGF)0$$aDoğan, Samed$$b12
001052307 7001_ $$0P:(DE-HGF)0$$aDerajic, Bojan$$b13
001052307 7001_ $$0P:(DE-HGF)0$$aFlohr, Fabian$$b14
001052307 7001_ $$0P:(DE-HGF)0$$aGalesso, Silvio$$b15
001052307 7001_ $$0P:(DE-HGF)0$$aGanzer, Malte$$b16
001052307 7001_ $$0P:(DE-HGF)0$$aGottschalk, Hanno$$b17
001052307 7001_ $$0P:(DE-HGF)0$$aHeid, Dominik$$b18
001052307 7001_ $$0P:(DE-HGF)0$$aHeue, Falk$$b19
001052307 7001_ $$0P:(DE-HGF)0$$aHu, Tao$$b20
001052307 7001_ $$0P:(DE-HGF)0$$aHubschneider, Christian$$b21
001052307 7001_ $$0P:(DE-HGF)0$$aKästingschäfer, Marius$$b22
001052307 7001_ $$0P:(DE-HGF)0$$aKeser, Mert$$b23
001052307 7001_ $$0P:(DE-HGF)0$$aKhongsab, Peerayut$$b24
001052307 7001_ $$0P:(DE-HGF)0$$aKowol, Kamil$$b25
001052307 7001_ $$0P:(DE-HGF)0$$aKrause, Felix$$b26
001052307 7001_ $$0P:(DE-HGF)0$$aKromm, Edward$$b27
001052307 7001_ $$0P:(DE-HGF)0$$aLucente, Giovanni$$b28
001052307 7001_ $$0P:(DE-HGF)0$$aLukin, Artem$$b29
001052307 7001_ $$0P:(DE-HGF)0$$aMariani, Annajoyce$$b30
001052307 7001_ $$0P:(DE-HGF)0$$aMittal, Sudhanshu$$b31
001052307 7001_ $$0P:(DE-HGF)0$$aMousakhan, Arian$$b32
001052307 7001_ $$0P:(DE-HGF)0$$aMualla, Firas$$b33
001052307 7001_ $$0P:(DE-HGF)0$$aMolin, Adam$$b34
001052307 7001_ $$0P:(DE-HGF)0$$aNeuhöfer, Jonas$$b35
001052307 7001_ $$0P:(DE-HGF)0$$aNiemeijer, Joshua$$b36
001052307 7001_ $$0P:(DE-HGF)0$$aBernal, Christian Ojeda$$b37
001052307 7001_ $$0P:(DE-HGF)0$$aOmmer, Björn$$b38
001052307 7001_ $$0P:(DE-HGF)0$$aOurania Tze, Christina$$b39
001052307 7001_ $$0P:(DE-HGF)0$$aPeyinghaus, Sven$$b40
001052307 7001_ $$0P:(DE-HGF)0$$aPiecha, Pascal$$b41
001052307 7001_ $$0P:(DE-HGF)0$$aPrestel, Ulrich$$b42
001052307 7001_ $$0P:(DE-HGF)0$$aRamazzina, Andrea$$b43
001052307 7001_ $$0P:(DE-HGF)0$$aReichardt, Jörg$$b44
001052307 7001_ $$0P:(DE-HGF)0$$aRist, Christoph$$b45
001052307 7001_ $$0P:(DE-HGF)0$$aRitter, Werner$$b46
001052307 7001_ $$0P:(DE-HGF)0$$aRochau, Dennis$$b47
001052307 7001_ $$0P:(DE-HGF)0$$aSavarino, Fabrizio$$b48
001052307 7001_ $$0P:(DE-HGF)0$$aSchenkel, Philipp$$b49
001052307 7001_ $$0P:(DE-HGF)0$$aSchlauch, Christian$$b50
001052307 7001_ $$0P:(DE-HGF)0$$aSchmidt, Julian$$b51
001052307 7001_ $$0P:(DE-HGF)0$$aTaş, Ömer Şahin$$b52
001052307 7001_ $$0P:(DE-HGF)0$$aThiel, Laurenz$$b53
001052307 7001_ $$0P:(DE-HGF)0$$aVivekanandan, Abhishek$$b54
001052307 7001_ $$0P:(DE-HGF)0$$aWalz, Stefanie$$b55
001052307 7001_ $$0P:(DE-Juel1)200557$$aWang, Jiangtao$$b56$$ufzj
001052307 7001_ $$0P:(DE-HGF)0$$aWang, Zhaoze$$b57
001052307 7001_ $$0P:(DE-HGF)0$$aWiederer, Julian$$b58
001052307 7001_ $$0P:(DE-HGF)0$$aWinter, Katharina$$b59
001052307 7001_ $$0P:(DE-HGF)0$$aWunderlich, Carolin$$b60
001052307 7001_ $$0P:(DE-HGF)0$$aYadav, Harsh$$b61
001052307 7001_ $$0P:(DE-HGF)0$$aYao, Yue$$b62
001052307 7001_ $$0P:(DE-HGF)0$$aYang, Yutong$$b63
001052307 8564_ $$uhttps://nxtaim.de/publikationen/
001052307 8564_ $$uhttps://juser.fz-juelich.de/record/1052307/files/nxtAIM_Whitepaper_AutomotiveFM_D01.pdf$$yRestricted
001052307 909CO $$ooai:juser.fz-juelich.de:1052307$$pVDB
001052307 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180916$$aForschungszentrum Jülich$$b0$$kFZJ
001052307 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)192312$$aForschungszentrum Jülich$$b3$$kFZJ
001052307 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)200557$$aForschungszentrum Jülich$$b56$$kFZJ
001052307 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001052307 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x1
001052307 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001052307 980__ $$areport
001052307 980__ $$aVDB
001052307 980__ $$aI:(DE-Juel1)JSC-20090406
001052307 980__ $$aUNRESTRICTED