Dr. Parthasarathy Nadarajan

Senior Steering Control Engineer, ZF Group (Active Safety and Electronics US LLC)

Platform-Agnostic Application Deployment: Enabling SDVs High-Performance ECUs

The growing complexity of the vehicle technology stack is a key driver behind the shift toward Software-Defined Vehicles (SDVs). Achieving this vision requires developing applications that are both hardware- and platform-agnostic to maximize development efficiency and simplify integration. This talk underscores the role of standardized vehicle interface, particularly through the Vehicle Signal Specification (VSS), and the use of machine-readable function and integration data to enable seamless deployment across heterogeneous platforms such as Classic AUTOSAR, Adaptive AUTOSAR, and ROS2. It also examines efficient methods for integrating Simulink-based applications on high-performance ECUs using the open-source Eclipse Automotive API framework. As SDV architectures evolve, the discussion highlights the critical importance of robust mixed-criticality systems, especially for chassis and other safety-relevant domains. This talk also covers high-level strategies for safe, deterministic, and isolated deployment across diverse computing environments while preserving real-time performance.

Bio

Dr. Parthasarathy Nadarajan is a Senior Steering Controls Engineer at ZF Active Safety and Electronics US LLC, where he coordinates the development and validation of advanced steering control functions for major U.S. automotive OEMs. Prior to his current role, he served as a Function Architect at ZF Friedrichshafen AG, Germany where he played a leading role in demonstrating SDV concepts in EU-funded programs, streamlining cross-platform function integration, and driving strategies for modular software deployment. His work has resulted in multiple patents and publications at top-tier IEEE conferences such as IV, ITSC, IJCNN, and the Airbag Symposium. Dr. Nadarajan holds a Ph.D. in Computer Science from RMIT University, Australia, specializing in deep-learning-based traffic behavior prediction.