Hello,

I am in last third year undergrad and I need to pick a topic for thesis. In general, I want to work on AI with applications in games. Any topics you might have please share

Thank you

Hello,

I am in last third year undergrad and I need to pick a topic for thesis. In general, I want to work on AI with applications in games. Any topics you might have please share

Thank you

Find something you are interested in with a focus on what you are strongest in. Otherwise, we are all just guessing at your interests and skill set.

A couple of examples I took from aigamedev.com's latest newsletter:

Character Animation in Two-Player Adversarial Games
Wampler, K. Andersen, E. Herbst, E. Lee, Y. Popovi?, Z.
http://grail.cs.wash...al-control/tog/

Space-Time Planning with Parameterized Locomotion Controllers
Sergey Levine, Yongjoon Lee, Vladlen Koltun, Zoran Popovi?
http://www.stanford....acetime_tog.pdf

A Sparse Grid Representation for Dynamic Three-Dimensional Worlds
Nathan R. Sturtevant
http://www.aaai.org/.../view/4085/4415

A Particle Model for State Estimation in Real-Time Strategy Games
Ben George Weber, Michael Mateas, Arnav Jhala
http://www.aaai.org/.../view/4051/4420

Build Order Optimization in StarCraft
David Churchill, Michael Buro
http://www.aaai.org/.../view/4078/4407

I recommend you tanking up on motivation. Without motivation you can't do the research necessary. Either way, the key to success is reading, reading and more reading. If you can't decide on something yet, just read through light-weight stuff. Once you got your mind set on something, start dwelling through all the papers and possible parts of books, that you can find.
Once you have a solid understanding of a topic, you can start working on your own addition to it.
If you have no background in AI, you definitely want to shape up on the basics. For that you can check out videlectures.net and similar. Tons of online resources that cover the basics - Use them wisely ;)

How about an analysis on machine learning and game ai? Where do the lines blur? Does each borrow from the other? Etc..

Why not look into improving the performance of game AI? By performance I do not mean improving the execution of game AI, but more along the lines of improving stability of behavior mechanics. If you need something more specific, why not looking into pathfinding. The A* and Dijkstra algorithms have been around for a while now. You need only to look at some of todays AAA games to see that pathfinding is not perfect and there is always room for improvment.