Mapping 3D character location for tracking players' behaviour

1999

Abstract This paper investigates the integration of Artificial Intelligence techniques into video games, from the perspective of voice controlled adventure games. Speech-based interfaces would add new dimensions to the control of video games. However, the integration of speech raises several issues, such as the adequate level of interpretation that should be carried by the system.

The number of people playing digital games has risen sharply in recent years. This partly reflects a trend towards game design and development that is more inclusive of different player types. However, this inclusivity has tended to result in more emphasis on the aesthetic aspect of interactivity design, and less on the challenge framed by the mechanics or logic of game-play. Thus we see a need to learn and understand more about players. Every player has different play preferences and skills. Automated modelling could teach game developers much about these differences, to make improved game-play experiences. Yet the opportunity for player modelling seems largely ignored in industry since most games feature limited adaptive intelligence. Games researchers have addressed the task but a cohesive automated model of player types is still lacking, perhaps because artificial data is often used for validation. We hypothesise that models of player behaviour can be built which can differentiate between players in real-time and increase developers’ understanding of how types of players interact with their games. This thesis presents a multi-faceted player modelling methodology which integrates empirical and theoretical insights to contribute to the state of the art. First, a data-mining classification experiment is performed, to learn rules for distinguishing player types. A rule- set, classifying the player type Conqueror and its complement, is deployed in Pacman for validation. The second modelling approach attempts to predict the player’s moves by evaluating potential future game-states using Decision Theory. Sub-routines describing features of play-behaviour are adapted from the data-mining work to describe player utility, linking the two approaches through methodology. Both methods achieve good predictive accuracy. Also, analysis of results shows that valuable information on player behaviour can be extracted. In summary, our contribution is a novel means of building more player understanding into game development, or real-time play

Simulation & Gaming, 2009

Games technology has undergone tremendous development. In this article, the authors report the rapid advancement that has been observed in the way games software is being developed, as well as in the development of games content using game engines. One area that has gained special attention is modeling the game environment such as terrain and buildings. This article presents the continuous level of detail terrain modeling techniques that can help generate and render realistic terrain in real time. Deployment of characters in the environment is increasingly common. This requires strategies to map scalable behavior characteristics for characters as well. The authors present two important aspects of crowd simulation: the realism of the crowd behavior and the computational overhead involved. A good simulation of crowd behavior requires delicate balance between these aspects. The focus in this article is on human behavior representation for crowd simulation. To enhance the player experience, the authors present the concept of player adaptive entertainment computing, which provides a personalized experience for each individual when interacting with the game. The current state of game development involves using very small percentage (typically 4% to 12%) of CPU time for game artificial intelligence (AI). Future game AI requires developing computational strategies that have little involvement of CPU for online play, while using CPU's idle capacity when the game is not being played, thereby emphasizing the construction of complex game AI models offline. A framework of such nonconventional game AI models is introduced.

2004

Abstract – As the number of 3-dimensional immersive environments increases, the challenge of how to navigate intuitively within them becomes more prominent. This paper introduces an area-based masking approach to assess the user's performance within the 3D environ- ment. We apply this mask onto the user's trajectory image in order to accumulate a performance measure.

Proceedings of the 5th ACM SIGGRAPH …, 2010

Video games today increasingly situate play in imaginative 3D worlds. As a result, the industry devotes much time and effort to level design. However, this subject has received very little research. Documentation on the process of level design or how designers push or pull players through a level within a video game is very sparse. In this paper, we propose a set of design patterns for level design. The patterns were developed based on a process involving interviews with game designers as well as gameplay analysis of different games. We established face validity of these patterns through expert review; we also established reliability using inter-rater agreement. In addition, we also developed a timeline video annotation method based on these patterns. This visualization method provides a very effective approach to view players' play style and preference as well as level design problems. The patterns as well as the visualization method will be discussed in the paper.

IEEE Transactions on Games, 2019

In the last decade, many commercial video games have used planners instead of classical Behavior Trees or Finite State Machines to define agent behaviors. Planners allow looking ahead in time and can prevent some problems of purely reactive systems. Furthermore, some of them allow coordination of multiple agents. However, implementing a planner for highlydynamic environments like video games is a difficult task. This work aims to provide an overview of different elements of planners and the problems that developers might have when dealing with them. We identify the major areas of plan creation and execution, trying to guide developers through the process of implementing a planner and discuss possible solutions for problems that may arise in the following areas: environment, planning domain, goals, agents, actions, plan creation and plan execution processes. Giving insights into multiple commercial games, we show different possibilities of solving such problems and discuss which solutions are better suited under specific circumstances and why some academic approaches find a limited application in the context of commercial titles.

2007

This paper introduces an interface and architecture of a method for personality typing through analyzing intentions. The game records some features during the interaction with players in order to correlate their choices with their gestures, such as mouse tracking, and eye movement etc. Through a 3D interactive video game interface, we are combining an approach using neural networks system and the Enneagram theory of personality to produce a machine learning engine that is able of extracting some specific traits of intentionality of the user after one session of playing the game. We also report the results of this engine and its internal structure and discuss some theoretical and practical challenges.

2002

The development of technology for the capture and description of 3D human motion enables higher level analysis of this data for automatic recognition of both individual and aggregate movements. In an immersive environment, if virtual agents can quickly perceive body and group actions of live participants, training environments will become truly interactive and challenging for the trainees.

International Journal of Emerging Trends in Engineering Research , 2021

In making a path finding algorithm in a 3D game to determine the direction of the NPC agent towards the destination, the Djiksra algorithm, Depth First Search, Breadth First Search and so on, usually the shortest distance is directly proportional to the travel duration to the target point. In this study, a test will be made using a list marker point such as the Djiksra algorithm to get the shortest distance and fastest time to reach the destination, in making this algorithm the C# language is used and the Unity software is used. After experimenting with various list points in different places in two directions, it was found that the distance traveled is always directly proportional to duration. So the selection of the fastest or shortest path can be done with this list point marker algorithm.

Path planning is one of the classical computational tasks in video games. Virtual characters need to autonomously find a path from their current position to a designated goal position. This is usually solved by running the A* algorithm on a grid or a navigation mesh. However, in many modern games, strictly following the resulting path is not sufficient. More levels of planning are necessary to efficiently simulate realistic and advanced behavior, and the underlying data structure should support those levels. In this paper, we discuss a five-level hierarchy of planning in games. Furthermore, we present a framework that provides solutions for the three center levels: global route planning, route following, and local planning. It uses an efficient and flexible navigation mesh based on the exact geometry of the environment. Our framework can be extended to solve advanced path planning problems in future games. When used as an interface for higher-level semantic planning systems, it provides a comprehensive set of techniques for game developers and path planning researchers.