Agency: Department of Defense | Branch: Navy | Program: SBIR | Phase: Phase II | Award Amount: 849.98K | Year: 2014
This proposal describes a series of inter-related subprojects aimed at developing an empirical understanding of the MAGIC CARPET system, including its training requirements, effectiveness, and safety. An important overall objective is to estimate cost, throughput, and readiness considerations compared to conventional landing technology. To accomplish this, the work, including work in future studies, is organized according to Kirkpatricks four levels of learning evaluation. To address levels 1 and 2, we will design and execute a formal experiment aimed at developing an empirical understanding of the training and performance requirements of MAGIC CARPET as compared with conventional landing technology. We will address Level 3 by developing and planning the validation for a model for predicting the effects of different schedules of initial and refresher training, and by planning a transfer-of-training study that involves both live and simulated carrier landings. The level 4 investigation will be undertaken in future studies that will create a model of the organizational training pipeline for MAGIC CARPET.
Agency: Department of Defense | Branch: Air Force | Program: SBIR | Phase: Phase II | Award Amount: 1.00M | Year: 2014
As analysts and operators move from data to insights, tools are needed for supervisory control, command and control, and intelligence analysis. Intelligence, Surveillance, and Reconnaissance (ISR) requires the ability to navigate and interpret mounds of data to produce actionable decisions. Through the Urban Telepresence program, the Air Force Research Laboratory (AFRL) is redefining a concept of operations for ISR operations by enabling remote, virtual operators to interact with operational environments without being physically present. However, redesigning this workflow requires advancements to human-machine interfaces. To support this need, the Aptima team is developing the Sensor Operations via Naturalistic Interactive Control (SONIC) platform. SONIC is a multimodal user interaction framework optimized for use within highly immersive and data-rich environments to provide an intuitive, naturalistic way for users to interact and collaborate with distributed sensors, unmanned systems, and teammates in the operational environment. SONIC integrates an immersive multimodal workstation with a context-driven interaction service, and is built on top of scientifically-grounded human-machine interface guidelines for hybrid reality environments. Ultimately, the objective of SONIC is to enable analysts and operators to provide mission support in real-time from remote locations more effectively, without an increase in workload or a decrease in performance.
Agency: Department of Defense | Branch: Air Force | Program: SBIR | Phase: Phase II | Award Amount: 993.12K | Year: 2014
There is an increasing need for fast and accurate analysis of large volumes of disparate data containing critical information. Existing tools for information search, retrieval, and exploitation are inadequate because the tools have limited ability to (1) help the analyst understand the semantics within the information, (2) reveal the relationships between the information and the analytic task, or (3) demonstrate the best ways to fuse the information into an assessment. Cognitive biases that result from limitations inherent in human cognitive processes subconsciously influence intelligence analysis, and current tools provide little or no help to prevent these biases from influencing results. Aptima and our partners propose to further develop an Adaptive Workspace for Analyst Knowledge and Engagement (AWAKE) capability. AWAKE will provide the next generation of cognitive, knowledge-aided analyst support systems to promote a more effective human-machine partnership, enabling analysts to focus on what they uniquely do best as humans, while the autonomous system looks over their shoulder to provide them cognitive aid. AWAKE provides a capability for measuring the analyst"s level of rigor; automatically identifying indicators of cognitive biases and vulnerabilities, based on a semantic interpretation of the user"s interactions with the system; and personalized agents to support analyst activities.
Agency: Department of Defense | Branch: Air Force | Program: SBIR | Phase: Phase II | Award Amount: 990.83K | Year: 2014
The volume of data collected by Air Force ISR has exceeded the capacities of traditional analysis methods. New enhancements to the Air Force"s PCPAD intelligence cycle are, thus, critical to providing the analyst with the ability to strategically process, exploit and analyze the most critical information. Aptima"s SCAAN system seeks to enhance PCPAD by distributing data exploitation and analysis tasks across a network of semi-autonomous agents (i.e., processing software resources) efficiently managed by a command, control, and communication (C3) software organization. SCAAN ensures robustness of distributed data analysis by balancing agent workload and building resilience to failures. SCAAN supports accuracy and optimality of large-scale data analysis by efficiently partitioning a global search problem into distributed interdependent tasks across multiple agents. SCAAN also provides agents with autonomy for learning patterns in a distributed fashion, and reduces the time of analysis by implementing algorithms that minimize processing of irrelevant data and communication requirements. Additionally, SCAAN operates in a hybrid infrastructure, leveraging service-oriented and cloud-enabled frameworks to support processing of large-scale data in accessible and denied environments. In summary, SCAAN is a processing, exploitation and analysis tool to assist analysts in efficiently and accurately extracting critical information from large-scale, distributed, multi-modal, multi-source data.
Aptima, Inc. | Date: 2015-07-26
Embodiments of the subject invention comprise a computer based system and methods to collect and compare the attributes of a group of entities using data representing topic data of the entity and interaction data between entities. Embodiments of the invention comprise using minimally invasive means to automatically collect and model both an entitys attributes such as their knowledge/work/interest as well as model the social interactions of the entity together with a means to identify opportunities to influence changes in the entity attributes. Minimally invasive means to collect and model attributes include semantic analysis and topic modeling techniques. Means to model social interactions include social network analysis techniques that can incorporate location data of the entity. Embodiments of the invention further provide a sharable index of the attributes of the entities and the group of entities.