Hardware-in-the-Loop Autonomous Driving Simulation Without Real-Time Constraints

摘要

Simulation is a cornerstone of autonomous driving efforts, allowing testing to occur more rapidly and with significantly less risk than is possible with hardware platforms alone. Simulation systems must be able to emulate a variety of sensors including cameras and LiDARs in order to allow high-level software such as image processing and path planning to be tested. In this paper, we present a hardware-in-the-loop simulation system without real-time constraints. It is based on CARLA to give access to the sensors required to test high-level software, and incorporates compute hardware identical to that used on an autonomous vehicle platform in order to provide realistic constraints regarding available processing power. In addition, we explore the robot operating system based software framework used on the Formula SAE vehicle and its integration with the driving simulator. Finally, we validate the sensor outputs and vehicle dynamics of the simulated system against a physical autonomous driving hardware platform.