KI-FLEX: Reconfigurable Hardware Platform for AI-based Sensor Data Processing for Autonomous Driving

The partners working on the research project “KI-FLEX” are developing a powerful, energy-efficient hardware platform and the associated software framework for autonomous driving. This “KI-FLEX” platform is being designed to process and merge data from laser, camera and radar sensors in cars quickly and reliably by using methods of artificial intelligence (AI; German abbreviation: KI). As a result, the vehicle always has an accurate picture of the actual traffic conditions, can locate its own position in this environment and, on the basis of this information, make the right decision in every driving situation – thus making autonomous driving safe and reliable.

KI-FLEX Special Features of the Planned Hardware-Software Solution
  • Flexible and highly efficient system-on-chip (SoC) platform for multisensory environment recognition in automotive applications
  • Flexibly programmable, future-proof multi-core deep learning accelerator in the form of a chip (ASIC).
  • Algorithms for sensor signal processing and sensor data fusion based on the use of neural networks (NNs)
  • Novel positioning and calibration algorithms for information processing based on camera, lidar and radar sensors
  • New scheduling concepts for dynamic resource planning in order to utilize the full potential of all system components at all times
  • Methods and tools based on artificial intelligence to ensure the functional safety of the AI algorithms in the application and in the planned hardware-software system
  • System adapts independently to different operating conditions through dynamic reconfiguration, for example if individual sensors fail or malfunction
TUM Research Contribution

Developing new resource planning concepts for dynamic monitoring and static synthesis of the existing HW/SW components.

The resource planner job is calculation of design-time and run-time architectural proposal based on HW/SW properties, predefined requirements and optimization goals.

The resource planner focuses on :

  • Design-time: generating message routings and task mappings for specified automotive networks and automotive multi-core processors respectively while calculating time-triggered schedules for communication tasks and processes
  • Run-time: monitoring safety-critical parameters and mitigating run-time violations

Project Partners

  • Fraunhofer Institute for Integrated Circuits IIS (lead of the consortium)
  • beo Automotive Systems GmbH
  • Infineon Technologies AG
  • videantis GmbH
  • Technical University of Munich, Chair of Robotics, Artificial Intelligence and Real-time Systems
  • Fraunhofer Institute for Open Communication Systems FOKUS
  • Daimler Center for Automotive IT Innovations (DCAITI)
  • Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Chair of Computer Science 3: Computer Architecture

Funding

To learn more about KI-FLEX, please refer to:

Project Homepage 

Press Release of KI-FLEX

People

Publications

  • Hadi Askaripoor, Morteza Hashemi Farzaneh, and Alois Knoll. 2022. "E/E Architecture Synthesis: Challenges and TechnologiesElectronics 11, no. 4: 518. doi.org/10.3390/electronics11040518.[more...]
  • H. Askaripoor, M. H. Farzaneh and A. Knoll, "A Platform to Configure and Monitor Safety-Critical Applications for Automotive Central Computers," 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ), 2021, pp. 1-4, doi: 10.1109/ETFA45728.2021.9613692.[more...]
  • H. Askaripoor, M. H. Farzaneh and A. Knoll, "A Model-Based Approach to Facilitate Design of Homogeneous Redundant E/E Architectures," 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2021, pp. 3426-3431, doi: 10.1109/ITSC48978.2021.9565115.[more...]
  • Askaripoor, H.; Shafaei, S. and Knoll, A. (2021). A Flexible Scheduling Architecture of Resource Distribution Proposal for Autonomous Driving Platforms. In Proceedings of the 7th International Conference on Vehicle Technology and Intelligent Transport Systems - VEHITS, ISBN 978-989-758-513-5, pages 594-599. DOI: 10.5220/0010471605940599.[more...]
  • Hadi Askaripoor, Morteza Hashemi Farzaneh, and Alois Knoll. "Considering Safety Requirements in Design Phase of Future E/E Architectures." 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA). Vol. 1. IEEE, 2020.[more...]