Jason R. Stack

Automation for underwater mine recognition: current trends and future strategy

The purpose of this paper is to define the vision and future strategy for advancing the use of automation in underwater mine recognition. The technical portion of this strategy is founded on the principle of adapting the automation in situ based on a highly variable environment / context and the occasional availability of the human operator. To frame this strategy, a survey of past and current algorithm development for underwater mine recognition is presented and includes a detailed description on adaptive algorithms. This discussion is motivated by illustrating the extreme variability in the underwater environment and that performance estimation techniques are now emerging that are capable of quantifying these variations in situ. It is the in situ linkage of performance estimation with adaptive recognition that forms one of the key technological enablers of this future strategy. The non-technical portion of this strategy is centered on enabling an effective human-machine team. Enabling this teaming relationship involves both gaining trust and establishing an overall support system that is amenable to such human-machine interactions. Aspects of trust include both individual trust and institutional trust, and a path for gaining both is discussed. Overall aspects of the support system are highlighted and include standards for data and interoperability, network-centric software architectures, and issues in proliferating knowledge that is learned in situ by multiple distributed algorithms. This paper concludes with an articulation of several important and timely research questions concerning automation for underwater mine recognition.

Long duration autonomy for maritime systems: challenges and opportunities

Achieving long duration capabilities has long been an important goal of research in autonomous systems. Persistence can enable such systems to be on station to respond to events and situations that were unknown at the start of a mission. It can enable data collection in spatially and temporally variable environments over time scales appropriate for understanding a wide range of phenomena. Long duration systems have improved ability to cover large distances, travel in ways that minimize energy consumption, and go places that may not be practical for manned or shorter duration systems. Long duration is also an important part of the design trade space for minimizing the costs involved in achieving certain kinds of mission capabilities. This is particularly true when thinking of long duration in terms of entire systems and not just individual platforms. For example, a system with an infrastructure that supports autonomously keeping sufficient numbers of individual platforms on station continuously would fall within this category even if each platform or sensor had only limited persistence individually. Additionally, what constitutes long duration with regards to these challenges may vary significantly from system to system. Much work in the past has focused on extending system limitations through methods such as efficient management of resources, energy harvesting, detection, identification, and

Kernel-Matching Pursuits With Arbitrary Loss Functions

The purpose of this research is to develop a classifier capable of state-of-the-art performance in both computational efficiency and generalization ability while allowing the algorithm designer to choose arbitrary loss functions as appropriate for a give problem domain. This is critical in applications involving heavily imbalanced, noisy, or non-Gaussian distributed data. To achieve this goal, a kernel-matching pursuit (KMP) framework is formulated where the objective is margin maximization rather than the standard error minimization. This approach enables excellent performance and computational savings in the presence of large, imbalanced training data sets and facilitates the development of two general algorithms. These algorithms support the use of arbitrary loss functions allowing the algorithm designer to control the degree to which outliers are penalized and the manner in which non-Gaussian distributed data is handled. Example loss functions are provided and algorithm performance is illustrated in two groups of experimental results. The first group demonstrates that the proposed algorithms perform equivalent to several state-of-the-art machine learning algorithms on well-published, balanced data. The second group of results illustrates superior performance by the proposed algorithms on imbalanced, non-Gaussian data achieved by employing loss functions appropriate for the data characteristics and problem domain.

Building net-centric data strategies in support of a transformational MIW capability

The Mine Warfare (MIW) Community of Interest (COI) was established to develop data strategies in support of a future information-based architecture for naval MIW. As these strategies are developed and deployed, the ability for these datafocused efforts to enable technology insertion is becoming increasingly evident. This paper explores and provides concrete examples as to the ways in which these data strategies are supporting the technology insertion process for software-based systems and ultimately contribute to the establishment of an Open Business Model virtual environment. It is through the creation of such a collaborative research platform that a truly transformation MIW capability can be realized.

Transitioning Mine Warfare to Network-centric Sensor Analysis: Future PMA Technologies & Capabilities

The purpose of this paper is to outline the requisite technologies and enabling capabilities for network-centric sensor data analysis within the mine warfare community. The focus includes both automated processing and the traditional humancentric post-mission analysis (PMA) of tactical and environmental sensor data. This is motivated by first examining the high-level network-centric guidance and noting the breakdown in the process of distilling actionable requirements from this guidance. Examples are provided that illustrate the intuitive and substantial capability improvement resulting from processing sensor data jointly in a network-centric fashion. Several candidate technologies are introduced including the ability to fully process multi-sensor data given only partial overlap in sensor coverage and the ability to incorporate target identification information in stride. Finally the critical enabling capabilities are outlined including open architecture, open business, and a concept of operations. This ability to process multi-sensor data in a network-centric fashion is a core enabler of the Navys vision and will become a necessity with the increasing number of manned and unmanned sensor systems and the requirement for their simultaneous use.

Development of an Unmanned Maritime System Reference Architecture

The concept of operations (CONOPS) for unmanned maritime systems (UMS) continues to envision systems that are multi-mission, re-configurable and capable of acceptable performance over a wide range of environmental and contextual variability. Key enablers for these concepts of operation are an autonomy module which can execute different mission directives and a mission payload consisting of re-configurable sensor or effector suites. This level of modularity in mission payloads enables affordability, flexibility (i.e., more capability with future platforms) and scalability (i.e., force multiplication). The modularity in autonomy facilitates rapid technology integration, prototyping, testing and leveraging of state-of-the-art advances in autonomy research. Capability drivers imply a requirement to maintain an open architecture design for both research and acquisition programs. As the maritime platforms become more stable in their design (e.g. unmanned surface vehicles, unmanned underwater vehicles) future developments are able to focus on more capable sensors and more robust autonomy algorithms. To respond to Fleet needs, given an evolving threat, programs will want to interchange the latest sensor or a new and improved algorithm in a cost effective and efficient manner. In order to make this possible, the programs need a reference architecture that will define for technology providers where their piece fits and how to successfully integrate. With these concerns in mind, the US Navy established the Unmanned Maritime Systems Reference Architecture (UMS-RA) Working Group in August 2011. This group consists of Department of Defense and industry participants working the problem of defining reference architecture for autonomous operations of maritime systems. This paper summarizes its efforts to date.

Defining and using open architecture levels

Open architecture (OA) within military systems enables delivery of increased warfighter capabilities in a shorter time at a reduced cost.i In fact in todays standards-aware environment, solutions are often proposed to the government that include OA as one of its basics design tenets. Yet the ability to measure and assess OA in an objective manner, particularly at the subsystem/component level within a system, remains an elusive proposition. Furthermore, it is increasingly apparent that the establishment of an innovation ecosystem of an open business model that leverages thirdparty development requires more than just technical modifications that promote openness. This paper proposes a framework to migrate not only towards technical openness, but also towards enabling and facilitating an open business model, driven by third party development, for military systems. This framework was developed originally for the U.S. Navy Littoral and Mine Warfare community; however, the principles and approach may be applied elsewhere within the Navy and Department of Defense.

An adaptively generated feature set for low-resolution multifrequency sonar images

Many small Unmanned Underwater Vehicles (UUVs) currently utilize inexpensive, low resolution sonars that are either mechanically or electronically steered as their main sensors. These sonars do not provide high quality images and are quite dissimilar from the broad area search sonars that will most likely be the source of the localization data given to the UUV in a reacquisition scenario. Therefore, the acoustic data returned by the UUV in its attempt to reacquire the target will look quite different from the original wide area image. The problem then becomes how to determine that the UUV is looking at the same object. Our approach is to exploit the maneuverability of the UUV and currently unused information in the echoes returned from these Commercial-Off-The-Shelf (COTS) sonars in order to classify a presumptive target as an object of interest. The approach hinges on the ability of the UUV to maneuver around the target in order to insonify the target at different frequencies of insonification, ranges, and aspects. We show how this approach would allow the UUV to extract a feature set derived from the inversion of simple physics-based models. These models predict echo time-of-arrival and inversion of these models using the echo data allows effective classification based on estimated surface and bulk material properties. We have simulated UUV maneuvers by positioning targets at different ranges and aspects to the sonar and have then interrogated the target at different frequencies. The properties that have been extracted include longitudinal, and shear speeds of the bulk, as well as longitudinal speed, Rayleigh speed, and density of the surface. The material properties we have extracted using this approach match the tabulated material values within 8%. We also show that only a few material properties are required to effectively segregate many classes of materials.