Environmentally Conscious AI: Improving Spatial Analysis and Reasoning

Published on .

During GDC 2014 AI Summit in San Francisco, I presented a session with Ben Sunshine-Hill from Havok.

I also had the opportunity to participate to the infamous Turing Tantrums and Simplest Tricks sessions with two short rants.

Environmentally Conscious AI: Improving Spatial Analysis and Reasoning

As game worlds become more complex, game characters need to become more "aware" of their surroundings. These days, it is no longer sufficiently believable for an agent to merely walk through these environments. Believable movement demands so much more. Characters may now need to jump, climb, duck or vault in order to navigate through their world. Additionally, simply "being" in a space brings in issues with cover selection, visibility, positioning and other forms of spatial awareness. In the past, this often meant time-consuming manual markup of levels or highly constrained level designs, and it certainly didn't support dynamic environments! This session will show two different architectures being developed - one by Havok and one by MASA - to help automate those spatial issues in a way that is independent of level design.

GDC 2014 AI Summit - Environmentally Conscious AI: Improving Spatial Analysis and Reasoning

Watch on the GDC Vault - View on slideshare - Download the slides

The simplest trick in the book - Simple formation slot assignment

The best slides I ever produced!

This very short talk (<5 min) shows a rather simpler method to compute assignments to formation slots for a group navigating agents.

Download Open original

Turing Tantrums: AI Devs Rant!

This was fun, and prepared at the last minute!

Mine is at ~30 minutes and is about the curse of parametrization, a long lasting pet peeve of mine: "I can guarantee that you can't explain to me how to set those parameters".

GDC 2014 AI Summit - Turing Tantrums: AI Devs Rant!

Watch on the GDC Vault