Lehigh University

•  Home - Munoz-Avila
•  Home - HTNbots
•  Downloads
•  Related Papers



HTNbot is the result of a research project to demonstrate that Hierarchical Task Network (HTN) planning techniques can be used to effectively coordinate team-based strategies in a First-Person Shooter (FPS) game. This project is funded by the Defense Advanced Research Projects Agency (DARPA) and the Naval Research Laboratory (NRL). A paper describing the results of the experiments has been accepted by the First Annual Artificial Intelligence for Interactive Digital Entertainment Conference (AIIDE-05).

The FPS game used is Unreal Tournament (UT), which was developed by Epic Games, Inc. It uses a client/server architecture that allows different client programs to control the behaviors of bots. Originally, only the retail UT game is the client that could connect to the UT Server. A group at USC-ISI and CMU jointly developed the Gamebot project to create an API for other clients to connect to the UT server. Once these external clients are connected to the UT server, the server then sends information about the game states and the bots.

The UT client that uses the Gamebot API to communicate with the UT server and control the bots in an UT game is Javabot.

This project consists of integrating Javabot with an HTN planner, SHOP, to create the strategies for the bots to execute. HTNs were used to encode strategies that coordinate a team of bots in an UT Domination game and run them effectively using standard FSMs to encode individual bots behavior.

To download all necessary files to go the download section
For Installation and Compilating instructions, click here


©2002-2005 P.C. Rossin College of Engineering & Applied Science
Computer Science & Engineering, Packard Laboratory, Lehigh University, Bethlehem PA 18015