Multi-Scale Code Generation for Simulation-Driven Rapid ADAS Prototyping: the SMELT Approach

Abstract

Advanced Driver Assistance Systems (ADAS) matured into comprehensive hardware/software applications with exploding complexity. Various simulation-driven techniques emerged to facilitate their development, e.g., model-based design, driving simulators and virtual platforms. Moreover, multi-domain co-simulation standards arose to join such technologies and achieve fully virtual ADAS prototyping. Built upon these concepts, this paper presents the Static Multi-scale Export Layer Tool (SMELT), a retargetable “one-click” ADAS code generation facility. SMELT accelerates ADAS design space exploration by ensuring continuous refinement from the highest-level model representation down to embedded production code generation. To highlight its advantages, an ADAS library was rapidly prototyped using SMELT. Lastly, algorithmic and system-level analyses are presented, alongside simulation performance evaluation.