CAD2RL: Real Single-Image Flight without a Single Real Image — mentioned by alexleegk

Thu, 11 May 2017 20:10:03 GMT

That's what Sadeghi and Levine [1] do in their work. They train in simulation in a lot of randomly generated scenes. Since the drone is trained with such a diverse set of scenes, the learned policy generalizes to the real world. Also, note that the physics of the simulation doesn't even need to be realistic. Unless you are doing high-speed control or aggressive maneuvers, the challenging part is the perception and not the control. In the paper from OP, the controls are even high-level discrete actions: left, forward, right. [1] https://arxiv.org/abs/1611.04201

Paper and discussion history. A mention is not an endorsement.

CAD2RL: Real Single-Image Flight without a Single Real Image · HackerPapers discussions

CAD2RL: Real Single-Image Flight without a Single Real Image — mentioned by alexleegk