Supercomputing Challenge

Interim Report Guidelines

After the Kickoff Conference, you will have until Friday, December 15th, to refine your project and submit your interim report. This report should describe your project, your progress to date, and your expected results.

The interim report, which should be around 500 words in length, should expand on the information in your proposal. Please note that the interim report may not be a copy of the proposal that you submitted earlier.

The interim report should include the following information:

  • the definition of the problem,
  • your plan for solving the problem computationally,
  • a description of the progress you have made up to this time,
  • the results you expect to get,
  • and at leave five citations of information you have referenced.

Example of an Interim Report

(Team 64 from Alamogordo HS was a finalist in the 2000 - 2001 Challenge)

Team Number: 064
School Name: Alamogordo High School
Area of Science: Artificial Intelligence
Project Title: An Investigation in Conditional Decision Making

Problem Definition:
Artificial intelligence, although initially thought to be a fanciful representation of scientific concepts with little basis in fact, has been validated and its theories affirmed through the research and analysis of the logical foundations of its principles. Modern interpretations of the artificial intelligence theory have led scientific theorists to begin to accept the feasibility of ideas formerly thought to reside only in the realm of science fiction, such as advanced computerized decision making. In attempting this project, our group is undertaking the investigation and simulation of the concepts involving advanced computerized decision-making.

The goal of this project is to create a sophisticated computerized artificial intelligence system that enables the computer to think logically and formulate the best strategy for accomplishing a task. The computer will both make "educated guesses" in-simulation based on it's likelihood for a successful outcome, and compares this to previous attempts at success, so that the computer can successfully formulate the most effective strategy possible in a real time environment. This will empower the computer to think in the same general manner a human does in order to, in the most effective way possible, determine the best method for completing its function.

Problem Solution:
The environment in which this simulation would be conducted, is drafted from the avionics dogfight. The computer would be responsible for taking knowledge of enemy positions and previous failures/successes, and, using logical paths, decide both immediate decisions and a strategy for winning the simulation. The AI would decide the best method for flight, whereby subsequently positioning the plane behind the enemy so as to effect a kill. Using a series of "evaluators", the AI would determine the effectiveness of an action, log it, and refer to it to make the next decision. Eventually, two "intelligent" AI's will be pitted against each other in the simulation to test their interactions with each other.

Progress to Date:
Presently, a simulation has been constructed in which two players get one plane each with which to attack each other. A clear (no obstructions) 3D square map is set up in which the planes will "fly." The players start at opposite corners (in the x-y coordinate plane) of the map, and in the simulation, their goal is to destroy each other. The planes controlled by the players can move in all three dimensions, in order to out-maneuver each other and position themselves in good locations from which to effect a kill. The environment in which the planes move, the plane movement and attack algorithms, rudimentary physics, constructing/destroying planes and players, and other parts of the simulation have been coded. We also have a layout for displaying the simulation graphically through the OpenGL 3D programming API. We plan now to program Artificial Intelligence (AI) systems for the planes. Initially we will implement very simple AI: each plane will simply fly towards the other. Further development of the AI will continue in two areas, attack and evasion. Attack AI will be used to direct a plane in the most efficient way towards its target, and Evasion AI will be used to make a plane attempt to maneuver out of its attacker's line of fire as quickly as possible. The Attack AI will drive one player's plane, and the Evade AI will drive the other player's plane for testing purposes. Eventually, both AIs could be combined, and each plane could both attack and evade the other when necessary.

Expected Results:
After programming, testing, and refining of the artificial intelligence system being created in this project, this final system could blaze the trail for future, more advanced systems that could develop the "best" solutions for any given problem much more quickly and efficiently than could a human (these decisions would often be better than those a human would make, as well, because the computer can base its choices upon many more variables than a human could comprehend). Using such a technology, many tasks could be accomplished by computers alone. This technology could be implemented in unmanned spacecraft, mechanical probes entering areas too dangerous for humans to traverse, and even in machines that would perform household tasks. Such implementations would take input from the real world and logically decide what method of action would be the best to take, just as the players in the simulation described above take input from its simulated surroundings and determine the best route to success, and just as humans take input from their surroundings and formulate the best route to accomplish their goals.

Team Members: Chris Berger, Joseph Farfel, Mathew Hoppe, Vincent Hoppe and Scott Richardson

Sponsoring Teacher: Albert Simon

http://www.challenge.nm.org/archive/00-01/interims/064.shtml

For questions about the Supercomputing Challenge, a 501(c)3 organization, contact us at: consult1516 @ supercomputingchallenge.org

New Mexico Supercomputing Challenge, Inc.
80 Cascabel Street
Los Alamos, New Mexico 87544
(505) 667-2864

Flag Counter