2017-2018 Assessment of the Army Research Laboratory (2019) / Chapter Skim
Currently Skimming:
6 Sciences for Maneuver
6 Sciences for Maneuver
Pages 134-166
The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.
From page 134... ...
In general, research presentations and posters were professional, logical, content-rich, and useful. Clear growth in knowledge content by ARL researchers and support staff was demonstrated.
|
From page 135... ...
Four projects presented to the panel demonstrated a multifaceted strong effort in the area of automated and joint human-robot path planning. These efforts are autonomous mobile information collection using value of information-enhanced belief approach, context-driven visual search in complex environments, air-ground team surveillance for complex three-dimensional (3D)
|
From page 136... ...
Autonomous Mobile Information Collection Using a Value of Information-Enriched Belief Approach This project uses value of information (VoI) as a central organizing principle for robot planning.
|
From page 137... ...
This gives a statistical basis for semantic queries, such as looking for analogous concepts. The semantic vector space approach taken by this researcher has been found to be useful in other domains.
|
From page 138... ...
A small fleet of robots can, for example, maneuver so as to maximize communications connectivity subject to interception and threat constraints. Unsupervised Semantic Scene Labeling for Streaming Data This research could benefit by addressing the following: How and what will agglomerative clustering methods be integrated into?
|
From page 139... ...
Given its importance, other ground modeling issues could also be systematically addressed. Autonomous Mobile Information Collection Using a Value of Information-Enriched Belief Approach Injection of human knowledge can significantly increase the mathematical tractability of motion planning problems.
|
From page 140... ...
It will be important to stay in touch, as much as possible, with relevant work in those and other communities. This research could more fully utilize relevant semantic vector space literature in order to achieve the desired "Watson-like" reasoning.
|
From page 141... ...
As a whole, the projects demonstrate both challenges and opportunities for the efforts in this area. Wingman Software Integration Laboratory The Wingman Software Integration Laboratory project integrates autonomous control and targeting of an unmanned high-mobility multipurpose wheeled vehicle weapon system with a manned vehicle, resulting in a human-machine combat team.
|
From page 142... ...
The project has resulted in the creation of several technical reports; while there are no publications to date, this is not surprising, given the short period of this project. Data collection that is planned includes a simulation event at ARL to assess a warfighter machine interface for the roles in January-February 2018 and use of the Wingman System Integration Laboratory for training and human subjects' data collection during warfighter experimentation in June-August 2018.
|
From page 143... ...
One challenge to developing and maximizing the potential of these collaborations is the ability of ARL researchers to share code and data with extramural partners. ARL has had some success creating an Open Campus Initiative allowing extramural researchers to more easily work with ARL researchers.
|
From page 144... ...
The perception group's activities have focused around their fiscal year (FY) 2020 goal: "Semantic labeling of an increasingly larger vocabulary of objects and behaviors to permit a richer, more detailed description of the environment." Additional activities emphasize the practical aspects associated with ensuring correct spatial interpretation of sensory signals, so that the environmental descriptions are spatially accurate.
|
From page 145... ...
A topically related project integrates textual features during training to improve the performance of a deep learning-based activity recognizer. There is an opportunity for these two projects to enhance one another.
|
From page 146... ...
Challenges and Opportunities Perception research has gone from being model-based to data driven on the strength of statistical machine learning and deep learning algorithms. At the moment, industry needs to dominate the target application domains of researchers and the data being collected.
|
From page 147... ...
aeroelastic predictions of a semispan tiltrotor uses a state-of-the-art suite of structural and fluid computer codes, Helios, to computationally analyze aeroelastic models that exhibit whirl-flutter instabilities and correlate computed results with existing and future wind tunnel test data. In compliance with Reliance 21 (the overarching framework of the DoD's S&T joint planning and coordination process)
|
From page 148... ...
and enable haptic interfaces that can be a very valuable natural, human-interface output mode for medical applications and other high-workload roles. Aerodynamics at Low Reynolds Number The careful experimental work included in the project on aerodynamics of aggressive low Reynolds number flight deals with generating a large gust and determining the resultant flow field.
|
From page 149... ...
The most outstanding accomplishments include developing the adaptive and embedded intelligence that employs basic science principles to develop a product with wide range of applications in the Army, and combining studies of the cockroach motion with models and advanced mathematics to design better robots. The tiltrotor aeroelastic work using computational and wind tunnel models presents a grand challenge and, if successful, will undoubtedly have important consequences for Army and DoD rotorcraft.
|
From page 150... ...
The project on CFD/CSD aeroelastic predictions of a semispan tiltrotor could first use a simpler aerodynamic model to complete computations in time to impact the design and execution of the wind tunnel test and use the more sophisticated and time-consuming FUN3D computational fluid dynamics model later. The investigators could consider the following: a tiltrotor version of the recently ended UH-60A air loads program seeking improved tiltrotor modeling tools to accurately predict whirl-flutter stability, exploring other CFD solvers toward validating FUN3D results, and identifying desirable tiltrotor features that require better computational models (e.g., thin tiltrotor wing)
|
From page 151... ...
Some of the facilities at ARL are now among the best in the world. ARL has excellent research equipment, experimental facilities, and computational resources, including a spray combustion research laboratory, a small-engine altitude research facility, and a high-temperature propulsion materials laboratory.
|
From page 152... ...
Another example of the use of experimental facilities to resolve relevant practical problems is the use of the altitude testing facility in the resolution of the Gray Eagle turbocharger failure issue. Such accomplishments are commendable; however, care needs to be taken to ensure that experiments are well planned in terms of relevant dimensionless parameters rather than running an array of tests at various dimensional conditions.
|
From page 153... ...
2025+ Tactical Unit Energy Independence Concept This project articulated a significant effort for supporting the increased recharging needs for soldier equipment. The trend of speeding up the charging of lithium-ion batteries to 6-10 C rate needs to be matched with a power source for all the energy needed at silent mode.
|
From page 154... ...
Given that operations are associated with roughly 65 percent of a system's life costs (35 percent for system procurement) , it cannot be overemphasized how important logistics and sustainability are to future Army missions and making smart (self-sensing, self-adapting, and self-reporting)
|
From page 155... ...
, high-performance computing, event and damage signature identification, damage detection, damage evolution prediction, advanced algorithms, machine learning, model- and data-based risk assessment, new structures and vehicles, and additive manufacturing. The researcher combined key pillars of science in the work (i.e., theory, experiment, and computation)
|
From page 156... ...
This laboratory-based work directly supports the development of AE-based airframe damage detection and localization methods. The overall quality of this work is high.
|
From page 157... ...
The overall quality of this work is good. Embedded Self-Sensing Composite Materials for Army Vehicle Platforms The use of embedded self-sensing nanomaterials within composite materials for sensing the onset of material damage is of great value to Army vehicle platforms.
|
From page 158... ...
Here, model fidelity, purpose, and computational tractability need to be suitably examined to make essential tradeoffs. Because data from actual system degradations and failures are not readily available, or are time consuming and expensive to create, models are also needed in order to help train the new machine learning algorithms that are being (and will be)
|
From page 159... ...
Recurrent Neural Networks for Airframe Damage Prediction It would be good to examine the impact of environmental uncertainty considering, for example, interfering noise sources, stochastic vibrations at sensor locations, energy-absorbing characteristics of wall materials, temperature, and humidity. Aerodynamic Interactions Modeling for Coaxial Rotor Future work could address critical validation issues.
|
From page 160... ...
; and research and simulation work on the Wingman Software Integration Laboratory, which has a clear path to Army-relevant static and dynamic scenarios and multiple-machine and multiple-human interactions. The overall technical quality of the intelligence and control effort is good, and has shown continual improvement -- particularly since the 2016 assessment by the Army Research Laboratory Technical Assessment Board.
|
From page 161... ...
The research typically utilized an appropriate mix of theory and experimentation to arrive at well-reasoned conclusions. The Wingman Software Integration Laboratory was identified as a promising project potentially resulting in outstanding data and knowledge that could ultimately be transitioned to the field.
|
From page 162... ...
ARL has done a good job of disseminating its research through top-notch conferences and has formed strong collaborations with external partners. Given that much of the ARL perception research is currently being evaluated on commercial or public domain data sets with limited obvious relevance to Army missions, an open question is whether the ARL research will perform similarly when it is transitioned to Army applications.
|
From page 163... ...
; what major test-beds will be exploited; how younger scientists are working with more senior scientists; and what expertise will be developed in house versus what will be imported from industry, academia, and other laboratories. In addition, ARL could accelerate progress in related research areas by developing a strategy for centralizing internal expertise on nontrivial tools and techniques, such as methods for deep learning.
|
From page 164... ...
The tiltrotor aeroelastic work using computational and wind tunnel models presents a grand challenge and, if successful, will undoubtedly have important consequences for Army and DoD rotorcraft. Recommendation: To further enhance the quality of research work in the platform mechanics area, the ARL researchers should • Discuss the physics behind the computational and experimental models in terms of govern ing equations, constitutive relations (material models)
|
From page 165... ...
Recommendation: Research programs in the energy and propulsion area should include con sideration of the following: • Research should be described in terms of relevant fundamental dimensionless parameters. • Experiments should be planned in the space described by the relevant dimensionless parameters instead of planning in terms of physical quantities and then calculating the dimensionless parameters.
|
From page 166... ...
166 2017–2018 ASSESSMENT OF THE ARMY RESEARCH LABORATORY Recommendation: ARL should identify benchmarks that can be used to assess methods being presented and facilitate comparisons of ARL efforts as well as other state-of-the-art methods. These benchmarks should be ordered in terms of complexity of addressed scenarios (e.g., im ages and video clips)
|
Key Terms
This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More
information on Chapter Skim is available.