The Computer Architecture and Operating System group at the Barcelona Supercomputing Center aims at carrying out research on programming models for critical embedded systems in charge of controlling fundamental parts of cars, airplanes and satellites. Our work is mainly done in the context of bilateral projects with several processor companies as well as several European-funded projects. For a complete list of publications of the group in the last years, please visit: www.bsc.es/caos
The deployment of Artificial Intelligence (AI) based solutions to deliver advanced software functionalities is consolidating as a key competitive factor in several industrial domains. In the automotive industry, autonomous driving (AD) software is meant to support autonomous operation and decision making for all aspects in a vehicle, by processing of a massive amount of data coming from multiple sensors like cameras and LiDARs. The entailed computational requirements can only be matched by complex MPSoCs (Multi-Processor System on Chip) with generic and ah-hoc hardware accelerators. Moreover, the increasing complexity of AI-based software functionalities encourages the use of highly modular middleware frameworks such as ROS2, CyberRT, or Autoware, running on top of general-purpose and/or automotive operating systems. Performance and (timing) analyzability are two fundamental (and sometimes conflicting) requirements for this type of system, where extensive guarantees must be provided on the capability to deliver correct results in a timely manner, as dictated by domain-specific Functional Safety (FuSa) standards.
The current position is meant to cover a wide scope of activities to enable the analysis and deployment of cutting-edge AI solutions autonomous systems, on specialized middleware/runtimes, on top of industrially representative embedded devices. The candidate is expected to combine applied investigation and hands-on implementation covering both software and hardware level aspects, including: the functional and non-functional analysis, porting, and optimization of (possibly tailored) AI models within representative AD and autonomous operation frameworks, to meet performance and functional safety requirements on top of specialized and custom accelerators.
Key Duties
- Conduct a thorough study on state-of-the-art AI-based autonomous driving frameworks, covering both widespread AI models and non-functional (e.g. timing) requirements
- Familiarization with representative AI-based autonomous driving setup and simulation
- Design or tailor and optimize AI-models to support AI-based autonomous driving functionalities
- Identify and explore opportunities for optimization of both AI-models and platform configurations to meet performance requirements
- Devise software and hardware level solutions to improve performance and analyzability of AI-based autonomous frameworks
Data de tancament: Dimecres, 31 Juliol, 2024
Més posts de Recerca
Cap comentari:
Publica un comentari a l'entrada