Games must engage players by keeping them in the game flow. Tobetter define the game difficulty according to the player, GeneticAlgorithms can be used. One of the interesting characteristics ofGenetic Algorithm is that it is a non-deterministic algorithm. For theplayer’s vision, it means that enemies are unpredictable. By notknowing which NPCs he will face, the gameplay turns moreinteresting. Another amusing factor for gaming is its adaptability,causing NPCs to slowly struggle to find a way to beat the player. Thesetwo characteristics make Genetic Algorithms good tools to makegames more entertaining. This paper aims to demonstrate thisadaptation capability in the Survival Shooter, developed by Unityenterprise and modified by the author for the algorithmimplementation. As result, it shows that players could stay in the gameflow while playing against genetically modified enemies.

No abstract

Game Analytics is an important research topic in digitalentertainment. Data log is usually the key to understand players’behavior in a game. However, alpha and beta builds may need aspecial attention to player focus and immersion. In this paper, wepropose t he us e of player’s focus detection, through theclassification of pictures. Results show that pictures can be usedas a new source of data for Game Analytics, feeding developerswith a better understanding of players enjoyment while in testingphases .

There are several challenges when modeling artificial intelligencemethods for autonomous players on games (bots). NEAT is one ofthe models that, combining genetic algorithms and neural networks,seek to describe a bot behavior more intelligently. In NEAT, a neuralnetwork is used for decision making, taking relevant inputs fromthe environment and giving real-time decisions. In a more abstractway, a genetic algorithm is applied for the learning step of the neuralnetworks’ weights, layers, and parameters. This paper proposes theuse of relative position as the input of the neural network, basedon the hypothesis that the bot profit will be improved.

Autonomous vehicles are already a reality, and there are still severalchallenges to overcome. One important challenge for the adoptionof these vehicles is perceiving its surroundings. This necessity ofperception can be fulfilled by digital cameras. When working withdigital image processing, the quality will be limited by real-timeconstraints. As several works indicate, this real-time constraint forautonomous vehicles is at most 100ms per frame. Also, by improvingthe processing time, the chances of accidents involving autonomousvehicles may be decreased. This paper analyses the advantages anddrawbacks of semantic segmentation and also presents a study toimplement perception for autonomous vehicles by accelerating asemantic segmentation algorithm, also used by other works on thefield. To accelerate the algorithm, spacial parallelism will be used.