Césium question for RL

Hi all

We are finalizing our choice for a platform enabling vision based reinforcement learning.

I have therefore a couple of questions:

  • does Cesium has the capability to simulate what would see sensors (especially a specific camera and a lidar (depth map)) ?

  • can I run Cesium headless to have multiple agents running in the cloud for example (no visualization)

Cheers

Guillaume

Hi Guillaume,

does Cesium has the capability to simulate what would see sensors (especially a specific camera and a lidar (depth map)) ?

I’m not sure exactly what you’re looking for, but it is possible to with Cesium, though not the base engine. Contact todd@agi.com if you want to talk about a solution that can make use of sensors and depth maps.

can I run Cesium headless to have multiple agents running in the cloud for example (no visualization)

You cold have Cesium running across multiple instances. However, I’m not sure why you would want to do this. Cesium is intended for visualization.

Thanks,

Gabby