Goal-Oriented Action Planning (GOAP) är en AI-arkitektur som tillämpar ett måldrivet beteende åt agenter i spel. Mål uppnås genom att planer med åtgärder genereras med hjälp av en sökalgoritm. Syftet med denna rapport är att undersöka hur två sökalgoritmer, A* och IDA*, presterar under planering i GOAP. De experimenten som används är dels en miljö där agenter simuleras, samt ett test där planer genereras för samtliga implementerade mål utan rendering och simulering av agenter. Data som utvärderas är bl.a. planeringstiden, antal besökta noder under sökning och genererade planer. Utvärderingen visar en tydlig fördel till A*, som i snitt är 38 % snabbare än IDA* vid planering av åtgärder i GOAP. Slutsatsen blir att A* är den algoritm att föredra om prestanda är det som eftertraktas men IDA* kan motiveras för dess egenskaper, så som lägre minneskomplexitet. / <p>För tillgång till implementationen, maila f.helmesjo@gmail.com</p>

Goal-Oriented Action Planning, även kallat GOAP, är ett system för att styra beteende av artificiell intelligens. Systemet använder en sökalgoritm för att besluta vilket beteende som ska köras baserat på ett mål och ett antal åtgärder. Studien målsatte att undersöka vilken sökriktning som var mest lämpad för givet scenario. Undersökningen utfördes med hjälp av en simpel spelprototyp baserat på rollspel med stridsmekaniker. Totalt tre tester utfördes med olika scenarion och alla resulterade i att regressiv sökning var snabbare än progressiv sökning. Resultat för det mest krävande målet visade att progressiv sökning besökte 1724 %, 1100 % och 232 % fler noder än regressiv sökning för respektive test.

NPCs are in many games the foundation on which it operates. NPCs create the illusion of inhabitants or assign purpose to the player. Whatever they do, they represent characters. Introducing a character has a certain margin of error, as a poorly portrayed character may cause more damage than the NPC would add. Without creating a believable environment which would include the NPCs, immersion could be difficult. As such this thesis investigates the effect of different behaviours to NPCs. With the focus on how visual and logical behaviours affect the players’ perception of their believability. The experiment was conducted in a game of the RTS survival genre. With the visual behaviours selected from the games Banished[1] and Frostpunk [2] the logical behaviours were inspired by F.E.A.R [3]. In the experiment testers were used to test three versions of the artifact. The first acted as a default and was used as the starting point for the second version which introduced enhanced visual behaviours. The third continued and added a predictive functionality as logical behaviour. The tests concluded that the visual behaviours had a positive effect on perception but no conclusive evidence to suggest the logical behaviour had the same effect.

This thesis covers an implementation of an artificial intelligence (AI) system for cooperation between multiple AI-agents. It was done as a part of a master thesis in Media Technology and a master thesis in Computer Engineering at Linköping University, campus Norrköping. The aim of the project was to explore modern techniques in AI and also develop a platform where this AI is implemented for the upcoming educational purposes. The idea is that students can use the system as a base to extend, learn and implement their own AI algorithms. Based on a literature study in AI systems the decision was made to base APAC on the GOAP system, a scalable planning architecture designed for real-time control of autonomous character behavior in games. The result of the thesis is a virtual world, made in Unity3D and C#, where the system is being used by virtual agents to build a city.

An architecture for actionbased planning and cooperation between multiple AI-agents based on the GOAP-architecture was developed together with a system to be used in advanced AI-courses at Linköping unversity. The architecture was implemented in this system to show the possibilities of our work.

The field of artificial intelligence has gained much knowledge through the implementation of decision-making systems in video games. One of these systems was the Goal Oriented Action Planning system (GOAP) which directs the behavior of an AI-agent through multiple digital artifacts categorized as goals, actions, and plans. The aim of the thesis is to aid in the understanding and creation of GOAP driven AI-agents in a video game setting to promote research on this topic. The research question of this thesis was about finding out how the GOAP architecture compares to other video game decision-making systems. The theoretical framework introduces the concept of the illusion of intelligence in video games and presents a discussion focused on the different components which make up a GOAP system and other components that support it. Additionally, the theoretical framework explains the need for a comparison between different decision-making systems and explains the social impact of game AI research. The methods section introduces the criteria for the comparison between GOAP and other decision-making systems and presents a comparison process that was driven by a literature review. A GOAP system was designed for this thesis using the unified modeling language and concept maps. It was then implemented using C# code in a free-of-charge game engine called Unity. We present the pseudocode for the implementation of the GOAP system and show that this framework is a modular, customizable, and reusable system that enables AI-agents to create plans from a varied set of actions. Finally, the paper suggests further research within game decision-making AI and emphasizes the importance of game AI research for communities of game developers, hobbyists, and others who could benefit from game AI in their projects.