What is the best way to add ray cast to observations? Learning Agents 5.4

[Delladep]

Hello,

I’m currently working on training agents capable of navigating from point A to point B while avoiding obstacles. Currently, I’m employing Lane Tracing by Channel to generate an array of location and distance values describing each ray, simulating the agent’s vision. Subsequently, I construct a static array observation using this data. Is this the correct way to do this kind of thing??

Thank you!

[Deathcalibur (Brendan Mulcahy)]

Yes, that’s exactly how you would do it!

Specify:

Make:

Let me know if that helps!
Brendan

[Delladep]

It works great! Thanks!