The game industry is moving into an era where old-style game engines are being replaced by re-engineered systems with embedded machine learning technologies for the operation, analysis and understanding of game play. In this paper, we describe our machine learning course designed for graduate students interested in applying recent advances of deep learning and reinforcement learning towards gaming. This course serves as a bridge to foster interdisciplinary collaboration among graduate schools and does not require prior experience designing or building games. Graduate students enrolled in this course apply different fields of machine learning techniques such as computer vision, natural language processing, computer graphics, human computer interaction, robotics and data analysis to solve open challenges in gaming. Student projects cover use-cases such as training AI-bots in gaming benchmark environments and competitions, understanding human decision patterns in gaming, and creating intelligent non-playable characters or environments to foster engaging gameplay. Projects demos can help students open doors for an industry career, aim for publications, or lay the foundations of a future product. Our students gained hands-on experience in applying state of the art machine learning techniques to solve real-life problems in gaming.

Player-Game interaction can be viewed as a sequence of game events between game systems and players. In each event, a piece of information (for example, a game challenge) is presented to the player, and the player responds to that information by executing proper in-game actions. Since different games have different systems and mechanics, it is difficult to analyze and compare game events across different games. In this paper, we propose an approach to measure the similarity between game events from different games quantitatively. This similarity information can then be used to transfer probabilistic models built for analyzing and generating game levels for one game to another game.

Human error is one of the most common causes of vul- nerability in a secure system. However it is often overlooked when these systems are tested, partly because human tests are costly and very hard to repeat. We have developed a community of agents that test secure systems by running standard windows software while performing collaborative group tasks, mimicking more realistic patterns of communication and traffic, as well as human fatigue and errors. This system is being deployed on a large cyber testing range. One key attribute of humans is flexibility of response in order to achieve their goals when unexpected events occur. Our agents use reactive planning within a BDI architecture to flexibly replan if needed. Since the agents are goal-oriented, we are able to measure the impact of cyber attacks on mission accomplishment, a more salient measure of protection than raw penetration. We show experimentally how the agent teams can be resilient under attacks that are partly successful, and also how an organizational structure can lead to emergent properties of the traffic in the network.

A presentation as an invited speaker for IEEE Cyberworlds 2003, the International Conference on Cyberworlds, Singapore.

This presents the latest design and implementation of the magnetic, angular rate, and gravity (MARG) sensor module. The MARG sensor module is designed for measuring 3-DOF orientations in real time without singularities. Each MARG sensor contains orthogonally mounted triads of micromachined rate sensors, accelerometers, and magnetometers for a total of nine sensor components. With an integrated microcontroller, the overall factor is less than one cubic inch. Digital data output rate is 100 Hz. To simplify calibration procedures and filtering algorithms, it is important that the response of the individual sensor components is linear within the typical operating regions. Experiments were conducted utilizing a precision tilt table and results indicate that all the sensor components are linear. A simple hand calibration method that requires no specialized equipment is also described. It was validated by experiments that indicate hand calibration produces results that are nearly equivalent to those obtained following precision tilt table calibration.

Article Share on Does the metaverse start now? Authors: Michael Zyda The MOVES Institute The MOVES InstituteView Profile , Robert Gehorsam Strategic Initiatives, There Inc. Strategic Initiatives, There Inc.View Profile , Philip Rosedale Founder & CEO, Linden Lab Founder & CEO, Linden LabView Profile , Mark Mine Walt Disney Internet Group Walt Disney Internet GroupView Profile , Mike Goslin Walt Disney Internet Group Walt Disney Internet GroupView Profile , JC Herz Author (Joystick Nation) Author (Joystick Nation)View Profile Authors Info & Claims I3D '03: Proceedings of the 2003 symposium on Interactive 3D graphicsApril 2003 Pages 215–218https://doi.org/10.1145/641480.641521Online:27 April 2003Publication History 1citation728DownloadsMetricsTotal Citations1Total Downloads728Last 12 Months149Last 6 weeks12 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

If you go strictly by the number of young adults playing it at all hours, it's a success. But how does America's Army, the US Army's free PC game strategic communications tool, fare in the real world of costs and benefits? The answer is gratifying and the quality is award winning.

The availability of inexpensive and powerful graphics cards as well as fast Internet connections make Networked Virtual Environments viable for millions of users and many new applications. It is therefore necessary to cope with the growing heterogeneity that arises from differences in computing power, network speed and users' preferences. This paper describes an architecture that accommodates the heterogeneity mentioned above while allowing a manager to define system-wide policies. Policies and users' preferences can be expressed as simple linear equations forming a mathematical model that describes the system as a whole as well as its individual components. When solutions to this model are mapped back to the problem domain, viable solutions that accommodate heterogeneity and system policies are obtained. The results of our experiments with a proof-of-concept system are described.

Networked virtual environments enable us to grow from using single-player machines to interacting across distances with players on other machines. Building a networked virtual environment is a significant software development effort, but we are getting to the point where we can build some systems routinely. This course provides an overview of the current state-ofthe-art with respect to networked virtual environments, where the hard research work is yet to be done and a hands-on introduction to the NPSNET-V. NPSNET-V is a research effort intended to investigate dynamically extensible, large-scale virtual environments. It is a follow-up to the successful NPSNET-IV project and builds on the lessons learned in that effort. The NPSNET-V effort includes research in support for the dynamic loading of simulation components across the network, the dynamic modification of object behaviors and protocols, scalability in numbers of world clients and overall world size, persistence, and graphics standard agnosticism.

Presents an extended Kalman filter for real-time estimation of rigid body orientation using the newly developed MARG (magnetic, angular rate, and gravity) sensors. Each MARG sensor contains a three-axis magnetometer, a three-axis angular rate sensor, and a three-axis accelerometer. The filter represents rotations using quaternions rather than Euler angles, which eliminates the long-standing problem of singularities associated with attitude estimation. A process model for rigid body angular motions and angular rate measurements is defined. The process model converts angular rates into quaternion rates, which are integrated to obtain quaternions. The Gauss-Newton iteration algorithm is utilized to find the best quaternion that relates the measured accelerations and earth magnetic field in the body coordinate frame to calculated values in the earth coordinate frame. The best quaternion is used as part of the measurements for the Kalman filter. As a result of this approach, the measurement equations of the Kalman filter become linear, and the computational requirements are significantly reduced, making it possible to estimate orientation in real time. Extensive testing of the filter with synthetic data and actual sensor data proved it to be satisfactory. Test cases included the presence of large initial errors as well as high noise levels. In all cases the filter was able to converge and accurately track rotational motions.

Rigid body orientation can be determined without the aid of a generated source using nine-axis MARG (Magnetic field, Angular Rate, and Gravity) sensor unit containing three orthogonally mounted angular rate sensors, three orthogonal linear accelerometers and three orthogonal magnetometers. This paper describes a quaternion-based complementary filter algorithm for processing the output data from such a sensor. The filter forms the basis for a system designed to determine the posture of an articulated body in real-time. In the system the orientation relative to an Earth-fixed reference frame of each limb segment is individually determined through the use of an attached MARG sensor. The orientations are used to set the posture of an articulated body model. Details of the fabrication of a prototype MARG sensor are presented. Calibration algorithms for the sensors and the human body model are also presented. Experimental results demonstrate the effectiveness of the tracking system and verify the correctness of the underlying theory.

As virtual environments have grown in size, increasing attention is being brought to the issue of filtering data that is of no interest to a given client.This filtering is known as interest management.Typically, interest management is thought of as a one step process: data flows in from the network, and either is rejected or accepted.This paper outlines a three-tiered approach to interest management, utilizing dynamic multicast group assignment based on a loadbalanced octree design.Initial prototyping suggests that it is possible to create virtual environments with the number of entities interacting in the environment at least an order of magnitude larger than previously demonstrated.

The virtual environment research community is focusing on the human computer interaction model for fully articulated 3D humans in the networked virtual environment. As that work moves forward there is the desire to internetwork large numbers of players. The NPSNET Research Group is in the forefront of that work and is focusing on the network and software architecture necessary to support large scale VEs. The paper presents a look at our multicasting and applications layer protocol research.

The Laboratory for Human Interaction in the Virtual Environment at the Naval Postgraduate School is one of the leading groups for the comprehensive study of humans in the virtual environment. The lab builds on work completed by the NPSNET Research Group to push the edge of human interaction. The HIVE Lab is additionally working towards the acceptance of a Masters program for this work at NPS and is driving the creation of the da Vinci Consortium for the study of humans in the virtual environment.

Article Free Access Share on NPSNET: a multi-player 3D virtual environment over the Internet Authors: Michael R. Macedonia Naval Postgraduate School, Department of Computer Science, Monterey, California Naval Postgraduate School, Department of Computer Science, Monterey, CaliforniaView Profile , Donald P. Brutzman Naval Postgraduate School, Department of Computer Science, Monterey, California Naval Postgraduate School, Department of Computer Science, Monterey, CaliforniaView Profile , Michael J. Zyda Naval Postgraduate School, Department of Computer Science, Monterey, California Naval Postgraduate School, Department of Computer Science, Monterey, CaliforniaView Profile , David R. Pratt Naval Postgraduate School, Department of Computer Science, Monterey, California Naval Postgraduate School, Department of Computer Science, Monterey, CaliforniaView Profile , Paul T. Barham Naval Postgraduate School, Department of Computer Science, Monterey, California Naval Postgraduate School, Department of Computer Science, Monterey, CaliforniaView Profile , John Falby Naval Postgraduate School, Department of Computer Science, Monterey, California Naval Postgraduate School, Department of Computer Science, Monterey, CaliforniaView Profile , John Locke Naval Postgraduate School, Department of Computer Science, Monterey, California Naval Postgraduate School, Department of Computer Science, Monterey, CaliforniaView Profile Authors Info & Claims I3D '95: Proceedings of the 1995 symposium on Interactive 3D graphicsApril 1995 Pages 93–ff.https://doi.org/10.1145/199404.199419Published:15 April 1995Publication History 56citation713DownloadsMetricsTotal Citations56Total Downloads713Last 12 Months25Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

No abstract available.

Abstract The Graphics and Video Laboratory of the Naval Postgraduate School (NPS) is in the process of constructing a three dimensional (3D) virtual world called NPSNET.1 NPSNET is a low‐cost, commercial workstation‐based 3D visual simulator that uses SIMNET terrain databases and networking.2 NPSNET is programmed using off‐the‐shelf SGI IRIS graphics workstations, rather than the platform‐specific nodes of SIMNET. Part of the work in constructing the NPSNET world is detecting and resolving collisions in real‐time. Such collision detection and resolution has been accomplished and integrated into the latest version of NPSNET, NPSNET‐2. The detection of vehicle‐weapon, vehicle‐vehicle and vehicle‐stationary non‐vehicle collisions is performed throughout the virtual world.

The development of 3D visual simulation systems on inexpensive, commercially available graphics workstations is occurring today and will be commonplace in the near future.Such systems are being constructed to move through and interact with 3D virtual worlds.There are a variety of goals for these systems, including training, planning, gaming and other purposes where the introduction of the physical player may be too hazardous, too expensive or too frivolous to be tolerated.We present one such system, NPS-NET, a workstation-based, 3D visual simulator for virtual world exploration and experimentation.

We present a study of a highly decomposable algorithm useful for the parallel generation of a contour surface display. The core component of this algorithm is a two-dimensional contouring algorithm that operates on a single 2 x 2 subgrid of a larger grid. An intuitive procedure for the operations used to generate the contour lines for a subgrid is developed. A data structure, the contouring tree, is introduced as the basis of a new algorithm for generating the contour lines for the subgrid. The construction of the contouring tree is detailed. Space requirements for the contouring tree algorithm are described for particular implementations.

Long-range route planning is an important component in the intelligent control system of an autonomous agent. Most attempts to solve it with map data rely on applying simple search strategies to high-resolution, node-and-link representations of the map. These techniques have several disadvantages including large time and space requirements. We present an alternative which utilizes a more intelligent representation of the problem environment. Topographical features are represented as homogeneous-cost regions, greatly reducing storage requirements. Then, the A* search strategy is applied to a dynamically created graph, constructed according to Snell's law. Testing has shown significant speed improvements over competing techniques.

Mobile autonomous vehicles require the capability of planning routes over ranges that are too great to be characterized by local sensor systems. Completion of this task requires some form of map data. Much work has been done concerning planning paths through local areas, those which can be scanned by on-board sensor systems. However, planning paths based on long range map data is a very different problem. Extant solution techniques require the search of discrete, node and link representations which characterize continuous, two dimensional problem environments. The authors assume the availability of topographic data organized into regions of homogenous traversal cost. Given this, they present a solution technique for the long range planning problem which relies on a Snell's Law heuristic to limit a graph search for the optimal solution

Recent articles have discussed the current trend towards designing raster graphics algorithms into VLSI chips. The purpose of these design efforts is to capture some of the real-time animation capability found in vector graphics systems. Currently, real-time vector graphics animation is limited primarily to operations involving coordinate transformations. In order to enhance this animation capability, frequently encountered vector graphics algorithms that require the high speed, parallel computation capability of VLSI must be identified. Real-time contour display generation from grid data is one such algorithm. This paper describes the specifics of a contour display generation algorithm, the architectural framework of a processor that performs this algorithm and the architectural requirements of such a processor.