ELIV 2024
Zusammenfassung
Content AI Automotive ASIL & GenAI How to Integrate GenAI in Automotive Enhance GenAI or Change Development Philosophy? 1 Speeding up Generative-AI in Software-Defined Vehicles 13 Automotive Trend Session AI Automotive Building and scaling a machine learning platform to unlock AI in connected car services 29 Quo vadis Vision Zero – Can AI help us to make our vision come true? 41 Auditing Guidelines for AI-based AD/ADAS Components focusing on AI Security 53 AI Automotive New Dimensions From Niche to Mainstream: Harnessing Generative AI for Automotive Excellence GenAI is not Enough! 67 AI in Traffic: New Dimensions of Vehicle Intelligence New method for optimizing traffic flow through AI-based implementation of real-world traffic data from other road users 81 Enabling Automotive MLOps with Open-Source Based Software 93 Automotive Trend Session Digital Homologation Statistical methods and Monte-Carlo simulation ensure the safety case of the environmental sensor performance in BMW’s first L3 function, the BMW Personal Pilot L3 105 The Path to Virtual Homologation Aspec...
Schlagworte
- Kapitel Ausklappen | EinklappenSeiten
- I–XIV Titelei/Inhaltsverzeichnis I–XIV
- 1–28 AI Automotive ASIL & GenAI 1–28
- 1–12 How to Integrate GenAI in Automotive Enhance GenAI or Change Development Philosophy? 1–12
- 13–28 Speeding up Generative-AI in Software-Defined Vehicles 13–28
- 29–66 Automotive Trend Session AI Automotive 29–66
- 29–40 Building and scaling a machine learning platform to unlock AI in connected car services 29–40
- 41–52 Quo vadis Vision Zero – Can AI help us to make our vision come true? 41–52
- 53–66 Auditing Guidelines for AI-based AD/ADAS Components focusing on AI Security 53–66
- 67–104 AI Automotive New Dimensions 67–104
- 67–80 From Niche to Mainstream: Harnessing Generative AI for Automotive Excellence. GenAI is not Enough! 67–80
- 81–92 AI in Traffic: New Dimensions of Vehicle Intelligence New method for optimizing traffic flow through AI-based implementation of real-world traffic data from other road users 81–92
- 93–104 Enabling Automotive MLOps with Open-Source Based Software 93–104
- 105–126 Automotive Trend Session Digital Homologation 105–126
- 105–116 Statistical methods and Monte-Carlo simulation ensure the safety case of the environmental sensor performance in BMW’s first L3 function, the BMW Personal Pilot L3 105–116
- 117–126 The Path to Virtual Homologation Aspects of the necessary framework for product safety in ADAS/AD 117–126
- 127–150 Software/SDV 127–150
- 127–132 Has the holy grail been found? Using Linux for safety-related applications 127–132
- 133–140 State-of-The-Art of Foundation Software for Software-Defined Vehicle 133–140
- 141–150 Managing the complexity of joint steering, braking and powertrain coordination in emerging vehicle E/E architectures 141–150
- 151–156 Software Open Source 151–156
- AUTOSAR and SOAFEE as Part of the SDV Alliance: Unifying the Software Defined Vehicle Ecosystem
- 157–220 Software Cloud, Connect & Rust 157–220
- 157–166 Automotive Vehicle Connectivity 2030 157–166
- 167–178 LightOpen – a cloud-based lighting personalization service 167–178
- 179–212 Bring TSN cloud native support to SDV architectures 179–212
- 213–220 Rust integration based on interoperability in legacy software 213–220
- 221–264 Processes SDV 221–264
- 221–232 SpecBook-Copilot – Efficient Formalization of Requirements using Artificial Intelligence in the Development of MB.OS 221–232
- 233–242 Using Simulation in the Development of V2X Applications CarMaker V2X Interface and Local Hazard Warning 233–242
- 243–256 Testing Variant-Rich Software-Defined Mobility Systems Methods, Future Challenges and Innovative Concepts 243–256
- 257–264 Optimizing Electronics Architecture for the deployment of Convolution Neural Networks using System-Level Modeling 257–264
- 265–302 Automated Driving 265–302
- 265–280 Using Large Language Models to generate critical driving situations for virtual and hybrid ADAS/AD testing 265–280
- 281–292 Ensuring ADAS functionality during periodic technical inspection ADAS/AD functionalities over a vehicle’s lifetim 281–292
- 293–298 Ensuring high reliability inside fail-operational systems Key prerequisite for SAE L3->L5 compliant automated driving 293–298
- 299–302 Importance of CATR technology in testing 4D imaging radars 299–302
- 303–312 Transformation of Working 303–312
- Collaborate with Chinese Partners to Navigate the SDV Transformation
- 313–358 Cockpit & Customer Experience In-Cabin 313–358
- 313–326 Immersive In-car AR Live Gaming Enabled by SDV Architecture, ADAS Cameras & AI Software 313–326
- 327–342 Biometrics and sensor fusion for enhanced in-cabin safety and comfort Reducing complexity and increasing possibilities through a holistic approach to in-cabin monitoring 327–342
- 343–358 Leveraging AI/ML Techniques in Software Defined Architecture: Towards Emotional Quotient Prediction in Smart Automotive Cabins by Integrating Physiological and Vehicle Data. AI-driven Smart Cabin in S... 343–358
- 359–394 Cockpit & Customer Experience Ecosystems 359–394
- 359–378 Generative AI based GUI reconfiguration using Natural Language Processing Leveraging the benefits of small and local LLMs 359–378
- 379–394 Electric vehicles in 2024. Current UX challenges and concepts for the coming decade 379–394
- 395–428 Mobility System Architecture 395–428
- 395–406 When innovation demand meets E/E architecture Further endeavours into next-gen architectural designs 395–406
- 407–418 Managing Reuse and Dependencies of Hardware and Software Components in SDV Architectures 407–418
- 419–428 Transition from Domain to Zonal Network Architecture for Software Defined Vehicles (SDV) 419–428
- 429–466 Processes/Virtual, Simulation, Requirements 429–466
- 429–436 Dead in 100 ms. Responsive (customer) functions require well-designed event chains and excellent timing requirements 429–436
- 437–452 A New Era for Software Verification: Heterogeneous Multicore Compute With Model-Based Design and Virtual ECUs 437–452
- 453–466 From Reality to Simulation: Automatized Transfer and Simulation of Critical Driving Scenarios with Digital Twins 453–466
- 467–482 E-Vehicle Mobility Vehicle Range 467–482
- 467–476 Battery-Integrated Multilevel Inverter Technology A Highly Integrated Electric Drivetrain Approach and its Technical Implementation in a Distributed Real-Time System 467–476
- 477–482 Boosting vehicle range by mating semiconductor technologies 477–482
- 483–516 E-Vehicle Mobility Charging 483–516
- 483–490 Integration of chargers and the grid How to Improve the Charging Experience of Your Customers by Better Integration with the Electricity Grid 483–490
- 491–504 Mapping the Future Role of Electric Vehicles as Energy Storage Systems: A Comprehensive Study on Current Market Trends and Future Projections for AC and DC Bidirectional Charging Detailed Review of Ma... 491–504
- 505–516 Advances in Electric Vehicle Charging Mapping between User Needs and Technology 505–516
- 517–540 Electronics Technologies 517–540
- 517–528 Automotive eFuses: Challenges of Today and Solutions for the Future 517–528
- 529–540 Enabling an Open Eco-System for Chiplet based Automotive SoCs Chiplets are the future for automotive SoCs and Road towards first Generations 529–540
- 541–564 Security TARA & More 541–564
- 541–552 TARAs Performed on Different Levels of the Supply Chain – Experiences Based on Real Example ESLF Insights into Applying ISO/SAE 21434:2021 in Automotive Cybersecurity 541–552
- 553–564 Efficiency in UNECE R155. Type Approvals for Small OEMS – Lessons Learned 553–564
- 565–XVI Security/AI 565–XVI
- 565–578 Recommendations for the practical use of Ethernet Security-Protocols and beyond 565–578
- 579–XVI Contribution of Artificial Intelligence in Automotive Cyber Security Management System More Cybersecurity through Artificial Intelligence 579–XVI
