Agency: Department of Defense | Branch: Navy | Program: SBIR | Phase: Phase I | Award Amount: 79.97K | Year: 2015
Automated Target Recognition (ATR) technologies offer potential for automated detection and recognition of targets of interest in imagery data with enhanced accuracy. Most existing ATR algorithms are trained on fixed datasets and cannot change during deployment. As a consequence, these ATR systems are likely to have degraded performance when deployed at unseen environments that are not covered by the training data. Whenever new data or new classes of targets need to be added, the baseline approach is to retrain the ATR system from scratch. Such offline retraining usually demands significant amount of computations which causes operational downtime, and is not suitable for online during-mission analysis. Current systems also lack an efficient framework to interact with operator for online learning and adapting to new environments.In this project, UtopiaCompression Corp. (UC) proposes to build a novel MUlti-spectral Visual Incremental Knowledge Assimilation System (MUVIKAS) as a software program that facilitates in-situ target detection and classification in multi-spectral imagery with human in the loop. The system self-adapts to varying scene backgrounds and to inputs from human operator, based on a novel incremental ATR algorithm that perpetually assimilates new and relevant information into the existing knowledge database in an incremental fashion.
Agency: Department of Defense | Branch: Navy | Program: SBIR | Phase: Phase II | Award Amount: 999.86K | Year: 2014
Optical perception is essential for USVs to accomplish its diverse range of missions while working autonomously on the surface of water. USVs should have the abilities of automatically seeing and avoiding obstacles as well as recognizing navigation lights and day shapes in other vessels. The current technologies lack the ability to satisfactorily capture images and process the digital data and fail to meet performance requirements in terms of stabilization, coverage, range and obstacle detection. In this Phase II UtopiaCompression Corp. (UC) and our collaborators will build a prototype of an innovative Intelligent Visual Sensing (IVS) system to support autonomous navigation and situational awareness of Unmanned Surface Vessels. Using a novel true omni-directional camera, the IVS system will provide a real-time video stream of panoramic images covering the full 360o cylindrical field-of-view (FOV) around the vessel with high image resolution and high image fidelity, free from parallax, distortion and artifacts. The IVS system will have intelligent video analytic capabilities of automatic detection, tracking and classification of surface contacts that enhance vessel situational awareness and support autonomous navigation It will thus free the operator from having to constantly watch and control pan-tilt-zoom cameras, which are extremely ineffective and cause fatigue.
Agency: Department of Defense | Branch: Air Force | Program: STTR | Phase: Phase I | Award Amount: 149.97K | Year: 2015
ABSTRACT: Over the past decade, there has been a sustained interest in Global Positioning System (GPS) denied navigation technologies for unmanned aircraft systems (UAS). This has been primarily due to the well accepted susceptibility of GPS signals to intentional jamming or unintentional interference and blockage. One of the challenging problems in GPS-denied navigation is handing off moving targets of interest between multiple UAS without the aid of GPS. Two problems must be solved to enable hand-off in denied environments, namely, estimation of relative pose and proper handoff between UAS. In this Phase I effort, we will develop a robust multi-phase handoff approach and examine its feasibility of handing off a moving target between UAS in GPS-denied environments. We will conduct Monte-Carlo simulations to evaluate the handoff algorithms and characterize how the estimation error of relative pose will affect handing-off performance.; BENEFIT: UCs proposed product offering will enable target handoff between multiple UAS in GPS denied environments. Therefore, it will offer a substantial ROI to users of small UAVs as it will maximize the utility of expensive and leveraged hardware investments by increasing actionable ISR derived from existent systems and expanding mission capabilities and operational environments even where GPS is not available. UCs proposed technologies will also enable more automated and efficient operations of multiple UAVs, decreasing operator loads. This will be of substantial use as pilots are currently overworked and in limited supply.
Agency: Department of Defense | Branch: Navy | Program: SBIR | Phase: Phase II | Award Amount: 749.84K | Year: 2013
Technological advances have significantly increased the complexity and speed of most operational environments resulting in escalating pressure on warfighters. There is an acute need for improved technologies to train and assess warfighters'cognition skills related to high-level tasks such as decision-making, planning and situation awareness. To this end, UtopiaCompression Corporation (UC) is proposing a suite of innovative modeling and assessment tools based on Adaptive Control of Thought-Rational (ACT-R) cognitive architecture that can be used to intelligently train warfighters and further provide relevant and personalized training remediation. In Phase I, UC has successfully demonstrated the advantage of using neuroimaging data to develop high resolution cognitive ACT-R models that account for warfighter's affect/emotions that considerably influence decision-making in HSCB and non-HSCB environments. During Phase II, our focus is to incorporate these high-fidelity models in a simulation environment to train forward observers using BAE Systems'training device. We will demonstrate the benefit of using high-fidelity models that can be personalized based on baseline subject measurements (neuroimaging and behavior data) and then be used independently to predict future trainee performance. Our solution must reduce the expert-in-the loop requirement for performance evaluation with significant reduction in subject/team training time and errors in decision-making.
Agency: Department of Defense | Branch: Army | Program: SBIR | Phase: Phase I | Award Amount: 99.94K | Year: 2015
Network modernization is one of the Armys top priorities. Tactical edge MANETs possess a set of unique challenges. Social metrics such as centrality and between-ness have proven to be useful in routing decisions in traditional MANETs. However, these routing protocols are based on link state information, which may become stale as the degree of mobility is increased, as in the tactical edge. Tactical edge networks possess some important characteristics that may be beneficial; for example, roles, organizational relationships, and mission plans. This a priori information can be translated into a set of mathematical objects that may be utilized by novel protocols. Such protocols would equip Army networks with heretofore untapped potential, ensuring information superiority for deployed forces. UtopiaCompression (UC) proposes a routing algorithm that exploits a priori mission information and operates independent of link state information. The a priori information is converted into a set of novel social metrics. Reducing the data to social metrics allows the routing problem to be formulated mathematically. UC, will design a hybrid social metric, based roughly on the Social-Tie concept, and associated protocols. The metric leads to a new definition of centrality tailored specifically to the tactical edge MANET.