Platform Intelligence

Platform Intelligence focuses upon fundamental research that enables effective teaming of Soldiers and robots to conduct maneuver and military missions. ARL’s activities are centered upon enhancing the autonomous capabilities of unmanned systems such as gps-denied navigation, agile all-terrain mobility, manipulation of the environment, and advanced agent-agent and human-agent teaming concepts. Knowledge gained in this area is expected to impact a wide array of vehicle systems, including the ground, air, and maritime domains, ranging from micro- to macro-scales.

Meta-Cognition, Self-Reflection and Proprioception (APG)

We develop novel techniques that enable embodied autonomous systems to track performance on assigned tasks that involve interaction with the physical world, recognize failures, and adapt or adjust performance.  While much of the work considers single systems, our goal is to develop systems that can work with teammates (both human and robotic) to accomplish physical tasks with minimal human oversight utilizing techniques from the fields of statistical learning theory, artificial intelligence, and perception.  Two topics of particular interest are recognizing and understanding teammate behaviors from visual and other sensory information; and developing a model of the physical system that enables the robot to reason about the effect of its body and the environment on physical tasks.

Principal Investigator:

MaryAnne Fields, Ph.D.,, (410) 278-6675

Integrating Perception and Cognition (APG)

Army systems that operate in unstructured dynamic environments require online adaptability that typically isn’t present in current state of the art robots. Our research integrates perception, cognition, mission planning and experiential knowledge to enable learning and performance based on past and current experience. While semantic perception, reasoning over uncertain knowledge and percepts, and adaptable planning are all required for a successful intelligent system, we focus on the bidirectional conduit between perception processes and cognitive processes that will enable incremental learning and flexible autonomy. Complementary expertise is especially sought in unsupervised learning and feature discovery, scene understanding, knowledge representation, object recognition and statistical relational learning.

Principal Investigators:

Jason Owens,, (410) 278-7023
Philip Osteen,, (410) 278-2057

Intelligent Vehicle Technology Experimentation (APG)

ARL conducts structured assessments of autonomous systems capabilities and technologies at various stages of development..  It applies the fundamentals of experimental design and applied statistics to enable assessment events that provide quantitative performance metrics and data.  Collected data is used to track progress of funded research, provide useful, objective feedback to the researchers, inform stakeholders about current and forthcoming capabilities, and validate autonomous systems performance in context.  Iteration on the experimental design and data capture methods are performed between the researchers and evaluators.  Experiments are primarily conducted at Aberdeen Proving Ground, MD. The team is able to travel to locations when relevant environments are required, the technology is currently not transportable, or when it is simply more expedient.  ARL-APG facilities include a 75’ x 450’ Unmanned Aerial System (UAS) runway with controlled airspace and an indoor 50’ x 30’ x 22’ Vicon motion capture area.

Principal Investigators:

Craig Lennon, Ph.D.,, (410) 278-9886
Marshal Childers,, (410) 278-7996

Computational Intelligence (ALC)

Research seeks computationally feasible techniques and theories to address the synergistic integration of components of intelligent behavior, including perception, reasoning, planning/execution, and decision making. These behaviors can be individual or collaborative. This includes: (1) semantic perception and scene understanding investigating innovative concepts for recognizing and understanding the world in which the system’s intelligent agents operate; (2) robot planning and behaviors in complex environments; (3) reasoning under uncertainty;

Principal Investigator:

Stuart Young, Ph.D.,, (301) 394-5618

Reasoning and Decision Making Under Uncertainty (ALC)

Research in developing a method for analogical and deductive reasoning and decision making by automated systems such as intelligence analysis systems or battlefield robots. In order to deal with the inherent uncertainty that comes with military operations, this approach needs to be able to handle approximate and partial information. Our method includes both a rich common-sense knowledge base for deductive reasoning and a distributional semantic vector space trained on large volumes of text corpora for analogical reasoning at query-time. This combination gives the system the ability to answer questions approximately when full information is not available. Our system can, for example, reason that because a tank is similar to a truck, it probably contains a steering mechanism and a transmission.

Principal Investigator:

Doug Summers-Stay, Ph.D.,, (301) 394 -1990

Atmospheric Characterization, Analysis and Effects [WSMR and ALC]

This research area seeks to fully-define atmospheric boundary layer physics, processes and climate variability, such as wind flow and turbulence generation in highly-complex terrain or in the urban street canyons of megacities. Theoretical and field studies are conducted to expand the knowledge-base about the precise workings of the near-surface atmospheric layer.  The characterization research will be greatly augmented by the implementation of the Meteorological Sensor Array (MSA). The MSA is a facility now under development and fielding; initially at two sites within and near White Sands Missile Range, NM; but potentially at an East Coast site as well.  This unique facility is comprised of a highly-dense deployment of meteorological sensors, active and passive, both for in situ and remotely-sensed data collection.  An understanding of the atmospheric characterization leads into research of those atmospheric and climatic effects on Army operations, infrastructure, and weapon systems to include renewable energy production systems.  It is vitally important that Army Commanders have a clear understanding of the atmospheric/climatic impact on their mission.  An important associated component of this research then, is the development of decision support applications which characterize and depict atmospheric and climatic impacts on systems, operations, and personnel; thereby providing battlefield commanders with readily-actionable intelligence information.  Development environments will include Soldier/system-level crowd-sourcing of meteorological data from mobile platforms, and technologies for mitigation of adverse environmental conditions.  Additionally, analyses will be conducted to identify statistical relationships between atmospheric conditions and battlefield events, and the likelihood of an event given the probability of the environmental conditions occurring.

Principal Investigators:

Robb Randall, Ph.D.,, (575) 678-3123

Artificial Intelligence for Autonomous Systems (APG and ALC)

Artificial intelligence (AI) and neural networks are playing a key role in Army autonomous systems, both virtual and robotic. Despite rapid application and development of AI for autonomous systems, there are many basic unresolved issues. Components, such as convolutional neural networks (CNNs), recursive neural networks (RNNs), kernel based learners, and auto-encoders, are empirically state of the art, yet we lack fundamental understanding of their performance limits, how much reliance on supervised training is needed, or how robust and resilient these components can be. These AI elements will be coupled with reinforcement learning and other techniques for incorporation into systems such as autonomous robotic navigation and surveillance, and human-machine dialog.  The invention and study of these emerging systems is critical for Army applications. In addition to the Human Agent Teaming and Artificial Intelligence and Machine Learning ERP, this work is also closely linked to the Distributed and Cooperative Engagement in Contested Environments ERP

Principal Investigator:

Brian M. Sadler, Ph.D.,, (301) 394-1239

Environmentally Aware Autonomous Unmanned Aerial Systems [WSMR]

This research area seeks to determine solutions for aggregate data handling and processing from multiple sources, including remotely (server-based) volumetric forecasts of adverse atmospheric impacts to the unmanned system, coupled with onboard sensors of the local environment. Disparate data sources introduce a problem on data handling and processing during execution of flight for a single drone, as well as conveying relevant information to drones within a swarm. As part of the optimization information, ARL’s Automated Impacts Routing (AIR), already demonstrated as part of an embedded system on a drone, will process the data (impacts and obstacles) for the path optimization portion/backend of the system.

Principal Investigator:

Jeffrey O. Johnson,, (575) 678-4085