High-Level Scenario Management For Parallel Autonomous Vehicle Simulation

Autonomous Vehicle (AV) simulations are ubiquitous and crucial for offline analysis and development of AV solutions. However, deploying and utilizing simulation technology at scale is, in practice, a constant challenge - especially for independent researchers with limited resources. This is compounded by the fact that publicly available simulators are fraught with poorly documented technical limitations which unnecessarily hinder adoption of these simulators. In this case study, we examine CARLA, a popular AV simulator with a rich feature set. CARLA provides an API and feature set which ostensibly offers the ability to run and manage an arbitrary number of simultaneous simulation instances for an indefinite period of time. This is essential for large scale data collection and offline AV solution testing. However, CARLA suffers from multiple unaddressed, poorly documented stability and scalability issues. These render these use cases impossible when performed naively. We outline a framework, along with code and best practices, for running an arbitrary number of CARLA simulations in parallel without manual oversight. This approach is generalizable to other simulators with similar challenges.