Hello everyone,
Thank you in advance for your time.
I am new in Isaac Sim. I would like to train a multi agent reinforcement learning algorithm for drone swarms. As part of the state of each agent, I was thinking about using a frontal camera (or another sensor, i.e. LIDAR).
I have seen the tutorial for Stable Baselines 3 and the GitHub repo ‘OmniIsaacGymEnvs’, but it seems that any of the examples are using a camera/sensor for the training.
Is there the possibility to initialize and then attach to a default asset (like a quadcopter) a camera with a fixed orientation and then use its observation as a part of the state?
Camera tutorial is quite handy for setting it while using simulator, but I can not find any Python implementation that shows how actually doing it directly with code.
Again, thank you for your answers.