This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Future Automotive Embedded Systems Enabled by Efficient Model-Based Software Development
Technical Paper
2021-01-0129
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Event:
SAE WCX Digital Summit
Language:
English
Abstract
This paper explains why software for efficient model-based development is needed to improve the efficiency of automakers and suppliers when implementing solutions with next generation automotive embedded systems. The resulting synergies are an important contribution for the automotive industry to develop safer, smarter, and more eco-friendly cars. To achieve this, it requires implementations of algorithms for machine learning, deep learning and model predictive control within embedded environments. The algorithms’ performance requirements often exceed the capabilities of traditional embedded systems with a homogeneous multicore architecture and, therefore, additional computing resources are introduced. The resulting embedded systems with heterogeneous computing architectures enable a next level of safe and secure real-time performance for innovative use cases in automotive applications such as domain controllers, e-mobility, and advanced driver assistance systems (ADAS). However, the increased system complexity challenges the efficiency of system verification during product development. The industry cannot afford delays in design cycles and efficient utilization of R&D resources is an important success factor. Model-based controls and software development with automatic code generation is an important dimension to resolve this challenge. It enables efficient algorithm development and verification and, thereby, supports to achieve ISO26262 compliance during product development. This is explained in this paper along three perspectives: Firstly, a use case overview explains the drivers for more advanced algorithms and, therefore, more high-performance computing resources. Secondly, a tool flow is proposed, which provides an efficient model-based controls and software development environment for next generation heterogeneous embedded systems. And lastly, this proposal is tested against automakers requirements for software and function development. Combining these perspectives sheds light on future automotive embedded software and systems, which experience an increasing relevance as demonstrated by recent automakers decisions to increasingly take ownership of software development.
Recommended Content
Authors
Citation
Schaefer, J., Christlbauer, H., Schreiber, A., Reith, G. et al., "Future Automotive Embedded Systems Enabled by Efficient Model-Based Software Development," SAE Technical Paper 2021-01-0129, 2021, https://doi.org/10.4271/2021-01-0129.Also In
References
- Meissner , F. , Shirokinskiy , K. , and Alexander , M. Jan. 2020 https://www.rolandberger.com/publications/publication_pdf/roland_berger_computer_on_wheels.pdf
- Garimella , G. , Funke , J. , Wang , C. , and Kobilarov , M. Neural Network Modeling for Steering Control of an Autonomous Vehicle IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Vancouver, BC 2017
- Prokhorov , D. Neural Networks in Automotive Applications Computational Intelligence in Automotive Applications 132 Prokhorov , D. Berlin, Heidelberg Springer 2008
- Nguyen , C. , Gutjahr , T. , Banker , A. , Burkard , D. et al. Hardware Supported Data-Driven Modeling for ECU Function Development Advances and Current Practices in Mobility 2 5 2948 2955 2020
- Synopsys, Inc. 2020 https://www.synopsys.com/designware-ip/processor-solutions/ev-processors.html
- Synopsys, Inc. 2020 https://www.synopsys.com/dw/ipdir.php?ds=arc-metaware-ev
- Firesmith , D. Using V Models for Testing 2013 https://insights.sei.cmu.edu/sei_blog/2013/11/using-v-models-for-testing.html
- Firesmith , D. 2015 https://insights.sei.cmu.edu/sei_blog/2015/03/four-types-of-shift-left-testing.html
- Stecklein , J.M. , Dabney , J. , Dick , B. , Haskins , B. et al. Error Cost Escalation through the Project Life Cycle 14th Annual International Symposium Toulouse 2004
- MathWorks 2020 https://www.mathworks.com/solutions/model-based-design.html
- Erkkinen , T. https://www.mathworks.com/company/newsletters/articles/how-to-use-simulink-for-iso-26262-projects.html
- MathWorks 2020 https://www.mathworks.com/products/system-composer.html
- MathWorks 2020 https://www.mathworks.com/products/matlab.html
- MathWorks 2020 https://www.mathworks.com/products/simulink.html
- MathWorks 2020 https://www.mathworks.com/products/deep-learning.html
- MathWorks 2020 https://www.mathworks.com/products/fixed-point-designer.html
- AUTOSAR 2020 https://www.autosar.org/fileadmin/user_upload/standards/classic/4-2/AUTOSAR_EXP_LayeredSoftwareArchitecture.pdf
- MathWorks 2020 https://www.mathworks.com/products/autosar.html
- Mathworks 2020 https://www.mathworks.com/products/embedded-coder.html
- MathWorks 2020 https://www.mathworks.com/help/releases/R2020b/ecoder/ug/what-is-code-replacement-ec.html
- Netlib Nov. 17, 2017 http://www.netlib.org/blas/
- Netlib Nov. 21, 2019 http://www.netlib.org/lapack/
- ONNX 2019 https://onnx.ai/
- TensorFlow https://www.tensorflow.org/
- The Khronos Group, Inc. 2020 https://www.khronos.org/opencl/
- MathWorks 2020 https://www.mathworks.com/products/simulink-requirements.html
- MathWorks 2020 https://www.mathworks.com/products/iec-61508.html
- Synopsys, Inc. 2020 https://www.synopsys.com/dw/ipdir.php?ds=sim_nsim
- Synopsys, Inc. https://news.synopsys.com/2020-10-27-Synopsys-Expands-Portfolio-of-Automotive-VDKs-with-Support-for-Infineons-AURIX-TC4xx-32-bit-Microcontroller-Family https://news.synopsys.com/2020-10-27-Synopsys-Expands-Portfolio-of-Automotive-VDKs-with-Support-for-Infineons-AURIX-TC4xx-32-bit-Microcontroller-Family
- MathWorks Simulink Test 2020 https://www.mathworks.com/products/simulink-test.html
- MathWorks 2020 https://www.mathworks.com/products/polyspace-bug-finder.html
- MathWorks 2020 https://www.mathworks.com/products/polyspace-code-prover.html