Advanced Driver-Assistance Systems (ADAS) is one of the primary drivers behind increasing levels of autonomy, driving comfort in this age of connected mobility. However, the performance of such systems is a function of execution rate which demands on-board platform-level support. With GPGPU platforms making their way into automobiles, there exists an opportunity to adaptively support high execution rates for ADAS tasks by exploiting architectural heterogeneity, keeping in mind thermal reliability and long-term platform aging. We propose a future-proof, learning-based adaptive scheduling framework that leverages Reinforcement Learning to discover suitable scenario based task-mapping decisions for accommodating increased task-level throughput requirements.
View on arXiv