5

Crosscutting Recommendations and Exceptional Accomplishments

CROSSCUTTING RECOMMENDATIONS

The following crosscutting conclusions, recommendations, and exceptional accomplishments are based on the projects and programs presented, as a full spectrum of projects and programs within each Army Research Laboratory (ARL) research core competency and the interrelating mapping across all research core competencies’ projects and programs were not provided to the Army Research Laboratory Technical Assessment Board (ARLTAB).

Four major changes to the Army and ARL clearly present challenges to all research core competencies. These are the recent Army doctrinal changes to Multi-Domain Operations (MDO), the reorganization that put ARL under the newly formed Army Futures Command (AFC), the divestiture of 6.3 work to other organizations, and emphasis on “disruptive” technologies. Specifically, ARL has been charged with focusing on foundational research; targeting and conducting research to drive change within, across, and between disciplines; creating knowledge products for warfighting concepts; development of operating systems; and interacting with universities via the ARL Open Campus and the Army Research Office (ARO).

With finite resources and the broad array of research topics being pursued by ARL investigators, the probability of final project success will be enhanced through cognizance of outside efforts and, where appropriate, establishing formal collaborations. Establishing contacts will require, at a minimum, attendance at professional meetings and conferences and possible travel to and from leading institutions.

There is significant attention given to artificial intelligence (AI) and machine learning (ML) in research programs across different portfolios at ARL. At present, the scope of these research efforts is rather narrowly focused on mission-critical tasks. Fundamental research issues related to innovative ML techniques, AI implementation in resource-constrained environments, and trust and security of AI systems must still be addressed on a broader scale. It is also important to recognize that it is suboptimal to seek algorithmic advances in these areas without due consideration of hardware developments that are taking place in parallel. Given the potential of a disruptive impact of these technologies on Army operations, it is important to develop a comprehensive and integrative research plan in this emerging area. These technologies can have a transformational impact on key elements of Army operations.

Software development has advanced at a tremendous pace over the past few years. Much of the reason for this rapid development is the increasingly common practice of employing open source software to build software platforms. Because of this rapid pace, it will be difficult for ARL to remain competitive within the software development space. ARL needs to be a member of GitHub (a major open source group—see https://github.com/) if it is not already. Of course, classified data needs to be handled in other ways.

EXCEPTIONAL ACCOMPLISHMENTS

The following are the exceptional accomplishments for each core competency area.

Network and Information Sciences

The research related to imitation was found to be particularly noteworthy, drawing upon the notion that autonomous agents can learn via imitation of human “teachers,” of which the Army has many. The two approaches (reinforcement learning and inverse reinforcement learning) are not new, but the research here addresses cutting edge technology, and the results are potentially disruptive. This represents a new way to automate. The demonstration of virtual reality was also viewed positively, with the recognition that notably high-quality experience could be disruptive for situational awareness related to Army operations. ARL could leverage the platform as a test-bed for ideas such as integration of satellite perspective, multiperson teaming, and human/agent teaming, and so on.

Some research projects were considered to be exceptionally strong and offer significant potential to contribute to U.S. Army capabilities. Research related to active defense and dynamic watermarking for cyber defense of vehicles and other cyber-physical systems was one such effort where commercial vendors are unlikely to provide solutions. This significant cyber vulnerability represents a pervasive problem in most major Army vehicles.

Another noteworthy project was in the area of narrative generation as it relates to human-robot interaction. The focus of this effort was in developing an understanding and explanation of visual scenery by extracting information and adding captions to video stills that describe relevant scene information and ultimately what transpired in the sum of correlated scene(s). This result alone, if successful, could provide the warfighter a significant workload reduction in processing full-motion video or still-frame imagery. While not the focus of the ongoing work, this research could potentially also save communications bandwidth by the transmittal of the textual descriptions of the scenes instead of the full-motion video.

Computational and Atmospheric Sciences

The artificial intelligence/machine learning at the edge: inferencing engines on field programmable gate array (FPGA) project concerns development of AI/ML inference engines that can be deployed as a digital chip (application-specific integrated circuit, or ASIC) in Army missions even when network connectivity is not available (e.g., for higher precision targeting). Further, when network connectivity is regained, learning online and training could resume to further enhance target solution quality. Such an ASIC-based online/off-line device could have multiple mission-relevant applications across the cross-

functional teams if the underlying systems design and engineering research and development (R&D) were to be successful. The technical approach involving a software framework, extensible instruction set architecture, and algorithm redesign/refactoring of convolutional neural nets (CNNs) seeks to reduce computational costs by an order of magnitude and increase efficiencies to meet space, weight, power, and time-to-solution constraints. This project spans the software-hardware space to deliver performance, portability, and programmability across multiple applications, future CNN algorithms, and future field programmable gate array (FPGA) architectures. Initial results seem encouraging, and there are many possible pathways to transition to the field while advancing the basic research. With improved direction, resources, and leveraging of related research, there is the potential for outstanding successes.

The work on improving numerical weather prediction over short time frames through assimilation of radar observations represents innovative research in support of an impactful real-world application and is especially noteworthy. ARL—collaborating with the Combat Capabilities Development Command (CCDC) Aviation and Missile Center, formerly known as AMRDEC—is developing a new mesoscale modeling capability that will provide forecasts in data-sparse regions such as the test facility on Kwajalein Atoll in the Pacific Ocean. Due to the site’s unique remote location, current Department of Defense (DoD) weather capabilities cannot meet these needs. The ARL approach assimilates radar observations already available at the location into the widely used weather research and forecasting (WRF) prediction model. Radar measurements of reflectivity are then used to infer rates of latent heating for input to WRF. Assessments of the new modeling capability demonstrate increases in probability of correct prediction of weather phenomena through assimilation of radar data by factors up to one order of magnitude.

Human Sciences

ARL has developed robust, contextualized human-autonomy teaming research laboratories, and has developed state-of-the-art synthetic task environments and data collection platforms through Cyber-Human Integrated Modeling and Experimentation Range Army (CHIMERA) and Information for Mixed Squads Laboratory (INFORMS). INFORMS has the potential to gather data that do not exist anywhere else on platoon-size teams. This could lead to very interesting science on platoon-size interactions, shared mental models, and attention allocation. In addition, the CHIMERA laboratory has outstanding metrics collection capabilities for cyber-human systems studies. ARL has significant experience and investment in neurophysiological measures to infer human states, as well as instrumented laboratories and simulation capabilities. Such advanced facilities promise to provide the ecological validity and experimental control needed to generate empirical evidence to address mission-critical research questions and advance the science of human-technology integration.

A significant achievement includes the collection and management of large data sets. Ambitious data collection activities—over time, between and within subjects, in the field—with target populations have created a number of large data sets that will be used to drive ML and simulation. The team has access to good information technology infrastructure to store and protect these organized and time-stamped infrastructure components. These researchers are pioneering something new.

The group has established a unique and valuable niche for engineering advances for neurophysiological monitoring in dynamic tasks, such as ambulatory electroencephalogram (EEG) and eye-gaze tracking. Specific contributions include novel algorithms for achieving accurate, reliable, and online detection of evoked response signals in the EEG while subjects are engaged in complex, operationally relevant activities. The group has also made novel contributions to the hardware and software technologies for EEG monitoring, particularly in mobile scenarios, which are prone to contamination from motion and environmental noise sources. The group has taken a rigorous approach to addressing these problems, developing a novel test-bed for isolating and eliminating sources of noise through innovative electrode and signal processing strategies. The group has also created unique testing platforms for studying human performance in complex tasks involving teaming among groups of humans

and autonomous vehicles in ecologically valid settings. These platforms are generating data sets that are unique and exceedingly rich in measuring physiological and behavioral aspects of human performance, spanning multiple time scales and modalities. In addition to supporting immediate questions, these data sets could be leveraged to support secondary analyses within and beyond the ARL mission space.

This page intentionally left blank.