Building an accurate aerial system simulator requires considerable expert knowledge on the related fields (e.g. aerodynamics [3]), and sometimes significant amount of computation time (e.g. Computational Fluid Dynamics).
In this work, we propose a simple aerial system simu-lation environment, which is built on top of a computa- tionally efficient 3D physics engine called MuJoCo [1].
We introduce some basic properties of our proposed en- vironment, which renders our environment as a testbed for simulation-based optimization of control, such as re-inforcement learning [2].