Shared and repeatable benchmark problems have historically been a fundamental driver of progress for scientific communities. In academic conferences, benchmarks, replication tracks, and competitions offer the opportunity to researchers, often with different origins, backgrounds, and levels of seniority, to quantitatively compare their ideas. In robotics, a hot and challenging topic is sim2real: Porting approaches that work well in simulation to real robot hardware. Hence, this article motivates and describes an aerial sim2real hardware–software framework that we created and used in: 1) a competition that ran during the 2022 IEEE/Robotics Society of Japan (RSJ) International Conference on Intelligent Robots and Systems (IROS 2022) and 2) two graduate courses, “Development of Unmanned Aerial Systems (AER1217)” at the University of Toronto during Winter 2023, and “Autonomous Drone Racing” at the Technical University of Munich (TUM).
Footer
