Quasim H. Mehdi

Shape of the story: story visualization techniques

There is now a growing awareness of the possibilities for application of natural language in the computing domain by incorporating knowledge of human-to-human interaction. We present an approach that aims to bridge the gap between scripting/storyboarding by a nontechnical creative writer and rendering characters and scenes by a graphics specialist. Natural language processing (NLP) and 3D graphic presentation is used to manipulate 3D scenes in real time. The proposed technique offers a flexible and easy way to generate an interactive 3DVE as compared with traditional 3D packages.

From visual semantic parameterization to graphic visualization

Visualizing natural language description is a difficult and complex task. When dealing with the process of generating images from natural language descriptions, we firstly should consider the real world and find out what key visual information can be extracted from the sentences which represents the most fundament concepts in both virtual and real environments. In this paper, we present the result of a prototype system called 3DSV (3D Story Visualiser) that generates a virtual scene by using simplified story-based descriptions. In particular, we describe the methodology used to parameterize the visual and describable words into XML formatted data structure. Then we discuss how to interpret the parameterized data and create an interactive real-time 3D virtual environment.

A new animation approach for visualizing intelligent agent behaviours in a virtual environment

Animated intelligent agents play an important role in dynamic virtual environments. They are able to perform behaviours based on internal states and external stimuli. Animation techniques are crucial to agent behaviour visualization in order to achieve effective interaction between agents and human users. This paper proposes a new animation procedure to visualise realistic intelligent agent behaviours. The animation system consists of three parts, namely synthetic vision, FzFSM with memory and an animation library that uses mesh skinning techniques. The agent is capable of exhibiting non-repetitive behaviours to reflect change from both its internal states and its environment. The system is implemented on a PC platform with modern 3D acceleration hardware. The result of this work can be applied to real time 3D graphics applications in the field of entertainment and multimedia.

Online action adaptation in interactive computer games

Nonplayer characters (NPCs) in todays computer games lack the ability to adapt to situations that were not envisaged by the artificial intelligence (AI) programmer. This lack of adaptation produces lifeless characters that are prone to repetitive and predictable behavior. In this article, we present our work towards the development of an online learning and adaptation architecture for NPCs in first-person shooter (FPS) computer games. Our architecture builds upon incremental case-based approaches to modelling an observed entity, and makes a number of novel contributions. In particular, we develop a dual state representation to enhance case matching, and use adaptive k-d tree-based techniques to improve case storage and retrieval. The dual state representation allows more game features to be represented in the system, which enables observed behavior to be more accurately recorded and actions predicted. The system is applied to the Unreal Tournament using the GameBots API and evaluated in a number of different game scenarios. Our results show that the adaptation system can accurately predict a human players actions and that our dual state representation enhances prediction. We also demonstrate that an adaptive k-d tree-based technique can be used online to maintain a balanced tree of observed cases.

In-game tactic adaptation for interactive computer games

Computer controlled characters in games typically lack the ability to adapt to situations that were not envisaged by the game artificial intelligence (AI) programmer. Consequently game characters tend to be lifeless and susceptible to repetitive and predictable behaviour. The focus of this work is to provide practical approaches to in-game learning and thus produce NPCs that are more believable and responsive to the human player. In this paper, we present an approach to online tactic learning and adaptation for autonomous agents in virtual environments. The design of the tactic adaptation architecture was influenced by commercial and theoretical approaches to the organisation and control of NPC behaviour in FPS games. The system is applied to Unreal Tournament using the GameBots API and evaluated in FPS game scenarios. The results show that the architecture is capable of successfully adapting NPC tactic selection and illustrate how a multi instance approach to organising tactic libraries can enhance adaptation.

Fuzzy-tuned Stochastic Scanpaths for AGV Vision

This paper details work on the development of an adaptive active vision system for an automated guided vehicle. An initial solution to the task of providing intelligent control of the saccades with which the AGV examines its environment is presented. A simple fuzzy logic technique suitable for implementation on a microcontroller is developed by using stochastic transition matrices. The results presented show the success of the technique in maintaining interest in objects previously located within the environment, locating new objects in an environment and making a compromise between the two.

Microcontroller based genetic algorithms

Abstract This work is concerned with the implementation of evolutionary based computer algorithms, genetic algorithms (GAs), on microcontrollers. Microcontrollers are low resource platforms not normally associated with GAs, which are typically resource intensive. This implementation will add to a suite of tools, based on different soft computing techniques, which will solve a range of optimization and decision-making problems that are essential in order for an autonomous guided vehicle (AGV) to carry out complex and highly involved tasks. Two examples are presented: path planning and the T-sequencing problem to demonstrate that the GA on an 8051 microcontroller is capable of carrying out necessary optimization and decision-making for AGVs.

Monitoring of patient fluid intake using the Xbox Kinect

This paper presents an approach that monitors patient fluid intake in real time. The approach utilizes the Microsoft Kinect, a low cost 3D sensor and the Microsoft Kinect Software Development Kit to monitor patient fluid intake. An implementation of the Naive Bayes Classifier is used to learn patient movement and classify new examples. The results from our initial experimentation show that the technique offers a promising approach to the monitoring of patient fluid intake.

Smart Terrain in Online Tactic Agent decision making process

Non-Player Characters (NPCs) are a vital part of computer games. Their behaviour is usually pre determined by the developers before a computer game is released. While these NPCs exist in a virtual environment in which they aim to achieve their objectives, these objectives might involve certain actions which should be both believable and add realism to games. In internet gameplay, these may range from navigation of the environment, attack and defense of an objective or assisting other NPCs or human players to achieve their goals. Various forms of decision making process are now implemented to provide believability and realism to games. These techniques range from reinforcement learning, imitation learning, supervised and unsupervised learning for online and offline games. While these are widely implemented, a new genre of realism is being added to games especially first person shooter games, namely Smart Terrains with virtual destructive environments. Smart Terrain has the potential to improve the realism of games and the behavior of the NPC in games such as first person shooter games where gameplay is fast paced. The potential issue would be if NPCs are dynamic enough to recognize changes in the virtual environment or if the virtual environment provides the required information to assist the NPCs with their objectives or tasks. This paper presents an overview of Smart Terrain in enhancing Online Tactic Agent decision making.

Navigational techniques to improve usability and user experience in RPG games

This paper presents the design and implementation of a mini map navigation system into an RPG Action Adventure game created using Unity3D game engine with the goal of improving the usability and user experience. The main aim of this work is to find out how a mini map navigation system can be beneficial to the end user and improve the over game play of a video game. The mini map can help reducing the user frustration, as well as aiding story progression so that it keeps the user immersed and engaged for a longer period of time that ultimately increasing the longevity of the game. A mini map navigation system is a user aid that is used across a wide range of video games and genres. The purpose of the map is to highlight the user position in relation to areas of interest such as objectives, enemies and Missions. A prototype game was created in the RPG Action Adventure genre with a vast open explorable world. The results show that the mini map has improved the overall usability and user experience.