This thesis explores the uses of a multi-agent system(MAS) for procedural content generation(PCG) in the Generative Design in Minecraft (GDMC) competition. The generatorconstructed is capable of surveying the terrain and determining where to start building a roadnetwork. Extendor and connector agents build the road network used for the settlement. Aplotting agent surveys the area around the created roads for plots appropriate for buildinghouses. A house building agent then generates basic buildings on these plots. Finally afurniture agent places furniture in these buildings. The result of the thesis shows that thegenerator is capable of generating an interesting road network that is appropriate to its terrain.The buildings have potential but are lacking in form of adaptability to the current biome andbuildings are overall too similar to be interesting, causing it to get low scores in the userstudy and competition. The generator was entered to the GDMC-competition in 2021 where itplaced 17th of 20th place.

This paper explores graph grammar and constructive solutions for settlement generation in Minecraft. It uses graph grammar to flatten parts of the surface in order to increase the space for the buildings. Buildings are then generated with a constructive solution that follows a step-by-step model where different parts of the building are created in a certain order. Different parts include the shape of the foundation itself, the walls, the roof and the furniture. The algorithm picks which blocks to use on different parts of the house through an object called district palette. The buildings are divided up into areas called districts, where all the houses within the district follow a similar aesthetic style. The goal is to compare our solution with existing solutions from the Generative Design in Minecraft (GDMC) competition to see how it holds up against the other submissions. To evaluate, a user study was performed where each jury has to score four criteria: adaptivity, functionality, evocative narrative, and aesthetics. The results show that the solution had a strong aesthetics but fell behind in adaptivity, functionality, and evocative narrative. Most of it was due to not being able to generate different structures, and not cleaning up the trees around the buildings and the roads.