http://www.movesinstitute.org/Plone daily 1 2006-10-06T22:53:32Z http://www.movesinstitute.org/Plone/copy_of_publications/towards-a-common-human-gesture-description-language Body gestures are of tremendous importance for human-computer interaction, in particular for user interfaces for mixed reality. In this paper, we suggest a way to unify efforts from various fields to describe body language and gestures. First, taking multidisciplinary experiences into account, desired characteristics of such a “common gesture language” are laid out. We then propose a flexible language that allows greater decoupling of gesture description sources from their uses, for example, for interaction with virtual and augmented environments. The paper is meant as an informed starting point for discussion. In Workshop Proceedings: Specification of Mixed Reality User Interfaces: Approaches, Languages, Standardization at IEEE International Conference on Virtual Reality, 2006 No publisher falby 2007-10-18T17:11:29Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/resource-aggregation-in-smart-sensor-systems We describe a network of diverse sensors and methods for capability discovery and resource aggregation. Camera nodes utilize the distributed sensors for selective image acquisition and processing. Compared to standalone cameras, these networked sensors consume less power and can be adjusted to heterogeneous and situation-specific resolutions by spreading them thinner or denser. Most importantly, however, diverse sensors can exploit a wider range of the electromagnetic spectrum. In field tests, our system behaved well above our expectations both in terms of detecting all events of interest as well as capturing images of interest. In Workshop on Distributed Smart Cameras (DSC), 2006 No publisher falby 2007-10-18T17:11:42Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/rapid-acquisition-of-persistent-object-textures Model generation for virtual and augmented reality environments is cumbersome, time consuming, and difficult. We present methods for rapidly texturing registered geometry and for quickly creating environment maps. The video from a tracked camera is projected onto the geometry and cached within the geometry’s textures. Object appearance thus becomes persistent beyond its momentary exposure to the video. The algorithms run in real-time and can be applied to arbitrary geometry. In IEEE Intl. Conf. on Virtual Reality (VR), 2007 No publisher falby 2007-10-18T17:11:54Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/particle-filters-and-simulacra-for-more-realistic-opponent-tracking Tracking the possible location of an opponent is a potentially important game AI capability for enabling intelligent hiding from or searching for the opponent. This article provides an introduction to particle filters for this purpose. Particle filters postulate a set of specific coordinates where the opponent might be as opposed to estimating probabilities that the opponent is in particular regions of the level, as is done in the occupancy map technique. By their very nature, particle filters have a very different performance profile from occupancy maps, and thus represent an interesting alternative. We also show how adding a small amount of intelligence to the particles, transforming them to simulacra, can improve the quality of tracking. In Game AI Programming Wisdom 4, Charles River, S. Rabin editor, 2008. No publisher falby 2007-10-18T17:11:03Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/multimodal-interaction-with-a-wearable-augmented-reality-system Wearable computers have evolved into tremendously powerful and versatile devices: PDAs, cell phones with integrated video recorders, wristwatches, game consoles, and even garments with built-in computational power. Unfortunately, their human-interface capabilities have not evolved as rapidly. Rather, the devices’ continuously shrinking form factors severely limit their interfaces. Traditional interfaces, such as keyboards and LCD screens, can only be as big as a device’s surface. Fortunately, the conflicting goals of device size and interface area can both be met by expanding the interaction area beyond the device’s dimensions: augmenting the reality through head-worn displays allows for information visualization in the entire field of view, extending far beyond the display’s physical size. Equally, hand gestures performed in free space, recognized with a headworn camera, are not constrained to the hardware unit’s dimensions. Combining these advantageous I/O modalities harbors the promise of more complex interaction than what is possible with a keypad. In this article, we detail our experiences with various input devices and modalities and discuss their advantages and drawbacks in the context of interaction tasks in mobile computing. We show how we integrated the input channels to use the modalities beneficially and how this enhances the interface’s overall usability. In IEEE Computer Graphics and Applications, May/June 2006, Vol 26:3 No publisher falby 2007-10-18T17:11:16Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/computer-graphics-based-target-detection-for-synthetic-soldiers The information provided to a software agent fundamentally affects its behavior. It is a trivial observation that an agent cannot respond to an environmental stimulus of which it is not aware. In a similar vein, providing an agent with information that a human participant in the simulation would not be aware of in the same circumstances may result in inaccurate agent behavior. In 3D virtual simulations, the most basic information provided to an agent concerns what battlefield entities that they can see. The standard approach used in 3D simulations with high visual fidelity, such as video games, is to use a line-of-sight (LOS) trace between entities to determine if they can see each other. LOS is arguably a very poor model of target detection, particularly in its failure to take camouflage, smoke, and darkness into account. In this paper, we describe a new approach that is an adaptation of a standard target acquisition model, to the domain of high visual fidelity simulations rendered on conventional graphics hardware. The new approach avoids the problems of LOS. We describe two variants of the approach, compare their predictions to human performance, and characterize their remaining deficiencies. In Proceedings of BRIMS 2007 (Behavior Representation in Modeling and Simulation). Recieved Outstanding Paper award No publisher falby 2007-10-18T17:10:36Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/individualized-npc-attitudes-with-social-networks This article introduces a method for largely automating NPC changes in attitude due to a player action. The method resolves the conflicting loyalties of the NPC’s to produce a single number per NPC that can be used to update the NPC’s feelings toward the player and drive future player-NPC interactions. The mechanics of the method are based on a constrained linear system, so it is computationally efficient, requiring only a single matrix multiplication in many applications. In Game AI Programming Wisdom 4, Charles River, S. Rabin editor, 2008 No publisher falby 2007-10-18T17:10:49Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/level-annotation-and-test-by-autonomous-exploration This paper proposes the use of an autonomous exploring agent to generate and annotate the waypoint graph as an offline process during level development. The explorer incrementally generates the waypoint graph as it explores the level via the same motion model used for player movement, and then revisits the waypoints to annotate them using image-based techniques. Points where the explorer becomes stuck or falls off of the level are flagged for later investigation by a level designer. In Proceedings of Artificial Intelligence in Interactive Digital Entertainment (AIIDE) 2007 No publisher falby 2007-10-18T17:09:15Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/game-ai-in-delta3d Delta3D is a GNU-licensed open source game engine with an orientation towards supporting “serious games” such as those with defense and homeland security applications. AI is an important issue for serious games, since there is more pressure to “get the AI right”, as opposed to providing an entertaining user experience. We describe several of our nearand longer-term AI projects oriented towards making it easier to build AI-enhanced applications in Delta3D. In Proceedings of Computational Intelligence and Games 2007 No publisher falby 2007-10-18T17:09:25Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/the-deployment-and-use-of-virtual-training-simulations-what-does-it-take-to-serve-the-needs-of-majority-of-its-users The potential and benefits that virtual training simulations have in supplementing the training needs of the military is fairly well recognized, yet we still do not see the evidence of their large-scale deployment. The way these systems are currently integrated in training fulfill the needs of two groups of users only - the innovators and early adopters - but they fail to fully serve the largest group of user population - the early and late majority. This session will elaborate on the requirements for most effective large-scale deployments and use, and present the results of extensive user studies in this domain. In Proceeding of the Society for Applied Learning Technology New Learning Technologies 2007 Conference No publisher falby 2007-10-18T17:08:32Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/finding-cover-in-dynamic-environments In this article, we describe our approach to improved cover finding with an emphasis on adaptability to dynamic environments. The technique described here combines level annotation with the sensor grid algorithm. The strength of level annotation is its modest computational requirements. The strength of the sensor grid algorithm is its ability to handle dynamic environments and to find smaller cover opportunities in static environments. Each approach is useful by itself, but combining the two can provide much of the benefit of both. In a nutshell, our approach relies on cover information stored in the candidate cover positions placed throughout the level whenever possible and performs a focused run-time search in the immediate vicinity of the agent if the level annotation information is insufficient. This allows it to be fast and yet able to react to changes in the environment that occur during play. In Game AI Programming Wisdom 3, Charles River, S. Rabin editor, 2006. No publisher falby 2007-10-18T17:08:47Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/a-mental-simulation-based-decision-making-architecture-applied-to-ground-combat At last year’s BRIMS conference, we described a model of mental simulation based on statistical event prediction (Kunde and Darken, 2005). In this paper, we describe a new decision-making architecture based on our mental simu-lation model. We have developed and tested the model using a scenario built in COMBAT XXI, where the model is used to make fire/hold fire decisions. While the choice of what is to be predicted and the basis for the prediction are chosen by a human modeler, the details of the predictive models are constructed by machine learning based on actual simula-tion data. Three different predictive models are used to support the decision, one for target richness, one for the effects of obscuring terrain, and one for losses. The outputs of the predictions are integrated by a decision component, which is currently implemented by a decision tree. Preliminary experimental results indicate that the predictive ability of the model and the resulting firing behavior are similar to human performance. In Proceedings of Behavior Representation in Modeling and Simulation (BRIMS) 2006. Received Outstanding Paper Award. No publisher falby 2007-10-18T17:08:59Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/combined-arms-training-methods-and-measures-for-a-changing-world It is clear that the way the military prepares for combat is rapidly changing. Doctrine and mission objectives are changing at a faster rate than ever before. The operational tempo is faster than it has been in the past. Yet leadership demands a prepared military force – no performance drop-off is acceptable. In fact, we will need to discover how to train in novel ways, in novel places, on novel tasks, to meet the requirements. While technology is not the whole answer to the puzzle, it must play a part. Determining how simulation and gaming technologies can be brought to bear on readiness will be key. Measures of effectiveness that equate to readiness are also needed. Much of what is done today is subjective in nature. There needs to be an improved mix of subjective and objective measures that can be used to “roll up” readiness from the individual on up to an entire force. Identifying opportunities for simulation and gaming that really improve individual and team performance and that are deployable so that they can be used in theatre are essential to success. Presented at the Research & Technology Organisation (RTO) Human Factors and Medicine Panel (HFM) Workshop held in United States Military Academy, West Point, NY, USA, 13-15 June 2006. No publisher falby 2007-10-18T16:32:59Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/extensible-3d-x3d-earth-technical-requirements-workshop-summary-report The initial X3D Earth Technical Requirement Workshop called together leading researchers, developers and industry experts to determine a broad set of technical requirements that will be necessary to construct an X3D Earth. This workshop was held 14-15 November 2006 at the Naval Postgraduate School (NPS) in Monterey, California, USA. The main goal in the creation of an Extensible 3D (X3D) Earth will be achieved by Web3D Consortium members who are preparing to build a standards-based suite of software tools usable by governments, industry, scientists, academia and the general public. X3D mappings of world terrain, cartography and imagery will be made available for use in any scene, making it easy to geospatially reference and share X3D models. Open standards, the Web architecture, utilization of the Extensible Markup Language (XML) and open protocols will be leveraged throughout. Both commercial and opensource software codebases will be able to utilize these best practices and contribute to these shared assets. The goal of this technical requirements workshop was for participants to identify and prioritize the technical requirements, available capabilities, open challenges and strategic partnerships needed for a Web3D working group to execute this ambitious project. Emphasis was placed on extensibly adapting existing resources and in cooperation towards achieving shared goals, especially with other open geospatial organizations and standards. These workshop results document participant contributions, next-step activities and goal milestones. The workshop concluded that X3D Earth is feasible and that the effort can be started now. Many resources are already available, yet work will be needed to make them compatibly available. No showstoppers were discovered; a nice surprise after so many diverse inputs. Finally, lots of collaboration and coordinated work are needed to proceed successfully in order to build a web-services infrastructure and develop a serverside specification to enable X3D Earth. No publisher falby 2007-10-18T16:16:43Z InventoryBuilder Item http://www.movesinstitute.org/Plone/copy_of_publications/exploring-a-chromakeyed-augmented-virtual-environment-for-viability-as-an-embedded-training-system-for-military-helicopters Once the military helicopter pilot deploys aboard a naval vessel he leaves behind all training platforms, short of the actual aircraft, that present enough fidelity for him to maintain the highest levels of readiness. To that end, this thesis takes a preliminary step in creating a trainer that places the pilot in an immersive and familiar environment to exercise myriad piloting tasks as faithfully and as rigorously as in actual flight. The focus of this thesis it to assess the viability of an chromakeyed augmented virtual environment (ChrAVE) trainer embedded into a helicopter for use in maintaining certain perishable skills. Specifically this thesis will address the task of helicopter low-level land navigation. The ChrAVE was developed to substantiate the viability of having embedded trainers in helicopters. The ChrAVE is comprised of commercial off the shelf (COTS) equipment on a transportable cart. In determining whether a system such as the ChrAVE is viable as a laboratory for continued training in virtual environment, the opinion of actual pilots that were tasked with realistic workloads was used. Additionally, empirical data was collected and evaluated according to the subject pool's thresholds for acceptable low-level navigation performance. No publisher rdarken 2007-01-04T00:06:59Z InventoryBuilder Item