J e f f    O r k i n
MIT Media Lab | Cognitive Machines

http://www.jorkin.com


Goal-Oriented Action Planning (GOAP)
 WHAT is GOAP?
Goal-Oriented Action Planning (aka GOAP, rhymes with soap) refers to a simplfied STRIPS-like planning architecture specifically designed for real-time control of autonomous character behavior in games. I originally implemented GOAP for F.E.A.R. while working at Monolith Productions. This A.I. architecture simultaneously powered Monolith's Condemned: Criminal Origins. (Brian Legge was responsible for the A.I. in Condemned). My GOAP implementation was inspired by conversations within the A.I. Interface Standards Committee's (AIISC) GOAP Working Group, as well as ideas from the Synthetic Characters Group's C4 agent architecture at the MIT Media Lab, and Nils Nilsson's description of STRIPS planning in his AI book.
 
 GOAP RESOURCES by JEFF ORKIN
[paper] [slides] 3 States and a Plan: The AI of F.E.A.R. (GDC 2006)
[paper] [slides] Agent Architecture Considerations for Real-Time Planning in Games (AIIDE 2005)
[paper] [slides] Symbolic Representation of Game World State: Toward Real-Time Planning in Games (AAAI Challenges in Game AI Workshop 2004)
Applying Goal-Oriented Planning for Games (draft for AI Game Programming Wisdom 2, 2003)
 
 GOAP RESOURCES by OTHERS
An Overview of the AI Architecture Inside the F.E.A.R. SDK - AIGameDev.com
Assaulting F.E.A.R.'s AI: 29 Tricks to Arm Your Game - AIGameDev.com
Special Report: Goal-Oriented Action Planning (membership required) - AIGameDev.com
How AI in Games Works: The Planning System - bit-tech.net
Practical Development of Goal-Oriented Action Planning AI - David Pittman's MS Thesis
Enhanced NPC Behaviour using Goal Oriented Action Planning - Edmund Long's MS Thesis
StarPlanner: Demonstrating the use of planning in a video game - Panagiotis Peikidis's B.Sc. Thesis
Threat Analysis Using Goal-Oriented Action Planning - Philip Bjarnolf's B.Sc. Thesis
Improved Missile Route Planning and Targeting using Game-Based Computational Intelligence - Ken Doris & David Silvia (CISDA 2007)
*Email me to add a resource.
 
 GOAP IMPLEMENTATIONS
F.E.A.R. SDK v1.08 - includes complete A.I. source code
*Email me to add an implementation.
 
This page last updated: 03/30/11
 GAMES USING GOAP ARCHITECTURES
F.E.A.R. (X360/PS3/PC) - Monolith Productions/VU Games, 2005
Condemned: Criminal Origins (X360/PC) - Monolith Productions/Sega, 2005
S.T.A.L.K.E.R.: Shadow of Chernobyl (PC) - GSC Game World/THQ, 2007
Mushroom Men: The Spore Wars (Wii) - Red Fly Studio, 2008
Ghostbusters (Wii) - Red Fly Studio, 2008
Silent Hill: Homecoming (X360/PS3) - Double Helix Games/Konami, 2008
Fallout 3 (X360/PS3/PC) - Bethesda Softworks, 2008
Empire: Total War (PC) - Creative Assembly/SEGA, 2009
F.E.A.R. 2: Project Origin (X360/PS3/PC) - Monolith Productions/Warner Bros, 2009
Demigod (PC) - Gas Powered Games/Stardock, 2009
LMNO (working title) (X360/PS3) - Electronic Arts
Just Cause 2 (PC/X360/PS3) - Avalanche Studios/Eidos Interactive, 2010
Transformers: War for Cybertron (PC/X360/PS3) - High Moon Studios/Activision, 2010
Trapped Dead (PC) - Headup Games, 2011
Deus Ex: Human Revolution (PC/X360/PS3) - Eidos Interactive, 2011
*Email me to add a game.
 
 RELATED RESOURCES
Creature Smarts: The Art and Architecture of a Virtual Brain - Synthetic Characters Group, MIT Media Lab (GDC 2001)
GOAP Working Group Report - 2004 AIISC Report
Planning Domain Definition Language (PDDL) - several versions linked from Drew McDermott's web page
Simple Hierarchical Ordered Planner (SHOP) - University of Maryland
Hierarchical Plan Representations for Encoding Strategic Game AI - Hai Hoang, Stephen Lee-Urban & Hector Munoz-Avila (AIIDE 2005)
SquadSmart: Hierarchical Planning and Coordinated Plan Execution for Squads of Characters - Peter Gorniak & Ian Davis (AIIDE 2007)
Connecting PDDL-based off-the-shelf planners to an arcade game - Olivier Bartheye & Eric Jacopin (ECAI AIG 2008)
*Email me to add a resource.
 
 RELATED BOOKS
AI Game Programming Wisdom 2 - Edited by Steve Rabin
AI Game Programming Wisdom 4 - Edited by Steve Rabin
Automated Planning: Theory & Practice - Paolo Traverso, Malik Ghallab, and Dana Nau
Artificial Intelligence: A New Synthesis - Nils J. Nilsson
Artificial Intelligence: A Modern Approach - Stuart Russell and Peter Norvig