Weekly Report 49

December 7th, 2009 by hale

Previous Week:
Submitted revised version of FLAIRS paper including corrections and improved experimentation.
Finished world component models and looked into lighting.
Implemented fine grain decompositions(sub 1 spacial unit object size) and layed ground work for variable growth step size
Generated navigation mesh for test world.

Currently Working on:
Finishing Proposal document
—Introduction is getting close to done
—Related works is coming along I had to do an extended literature search from a computational geometry perspective and found a large number of additional sources to look at.
Finish wiring interface for DEACCON
Geometric combining
3D validation and verification of results.
Generate ramp structure for Fritz to use to create more interesting levels.

Weekly Report 46

November 16th, 2009 by hale

Previous Week:

Nailed down design for FLAIRS paper motivation and experiment.

Constructed Several Block World components.

Implemented C++ version of dynamic rebuilding of decomps (in progress eta today)

Expanding visualizer to show agent movement and discovery of block world components, also enhanced visualizer with better exception handling.

Finished some typed proofs for Dr. Barnes – still have a few chapters to type up.

Planned Work

Complete and Run FLAIRs paper experiment target Wednesday

Finalize dissertation committee and submit first set of paperwork – target Wednesday

Filled in Dissertation outline – target required for finalization of committee members.

More proofs for Dr. B

Draft of FLAIRS paper target Friday

Interface work on DEACCON – target as time permits

Week of Nov 9th

November 9th, 2009 by hale

ToDo:
DEACCON work – interface more granular loading of models features for FLAIRS papers
Committee and PhD proposal setup targeting week of December 7th

FLAIRS paper
Hyp: It is possible to discover a navigation mesh using information gained from one or more agents moving through the world.

Applications: Simulations of Search and rescue in unknown environments, more “fair” agents for games and simulations, others

Approach: Crib some of the D* working with unknown areas and combine that with dynamic rebuilding of decomps. Assume world is empty then rebuild when this assumption is invalidated.

Validation and Experimentation: Compare the error levels present in a agents generated decomposition (incorrectly classified space, missed gateways, average path lengths) to the “optimum decomposition” in a time lapsed manor. How quickly does agent discovery converge on optimum decomp?

Weekly Report Oct 26

October 26th, 2009 by hale

ToDo

Paperwork – PhD review form, Proposal forms

Interface for C++ DEACCON

Halloween Gamenight

Plan for Week of October 5th

October 5th, 2009 by hale

Finish for AIIDE:
Generate SSPS for Fritz
Finish VASFV
Create UI for PASFV/VASFV
Create AI poster Draft by wednesday lunch for approval / revision
Smooth out any rough edges in PASFV/VASFV

Report for previous week

Finished Gems chapter and submitted draft.

Presented Friday Seminar.

Hello world!

September 21st, 2009 by hale

Welcome to Game Intelligence Group. This is your first post. Edit or delete it, then start blogging!

Week 19 Report

May 11th, 2009 by hale

Eng:

Worked on Behavior Shop.

Screen 2 is now done except for a few minor tweaks.

Assisted on fixing bugs in FI3Rst.

Week 18 Report

May 4th, 2009 by hale

Eng:

Heavy Engineering on implementation of behaviorshop1.0

View is completed or near final for every screen of BehaviorShop.

Model is also finished.

Control is done on screen 1, mostly done on screen 3, and I will be finishing it on screen 2 today.

Sci:

Some work on journal paper for metrics work

Started thinking about how to design, present, implement, and most importantly evaluate multilevel hierarchical ASFV 2D/3D.

Beginings of a proof that only 4 regions can come together at a point

April 22nd, 2009 by hale

It can be shown geometrically that the sum of the angles of all lines meeting at a point must be 360 degrees.  I can show that every exposed corner in my application is either 90 degrees, or in the case of edge following regions will when added to the angle of the edge they are following be 180 degrees.  This means I can prove an upper limit for regions coming together at a point of 4.

Weekly Report 16

April 20th, 2009 by hale

Engineering:

Fixing remaining bugs outstanding in DEACCON 3D

Produced images of 3D decomposition.

Performed comparison between multiple decomposition techniques.

Got dynamic creation of controls in wxPython working

Science:

Produced AIIDE paper.  Trimmed AIIDE paper.

Started reading for second half of qualifying exam.

Other:

Demo’ed for the friday speaker.

Took Qualifying exam written component