The U.S. Army has concluded an autonomous micro-robotics research project that involved collaboration between the Army Research Laboratory and multiple industry and academic partners over the past 10 years.

The Micro Autonomous Systems and Technology program was completed during a capstone event which featured 17 demonstrations and presentations of ground and air micro-robots, the Army said Monday.

BAE Systems led the MAST collaborative technology alliance and collaborated with NASA‘s Jet Propulsion Laboratory in efforts to integrate microsystems.

The University of Michigan, University of Maryland and University of Pennsylvania focused on microelectronics, microsystem mechanics and targeted processing for autonomous operations under the project.

“We’re now seeing a wave of commercialization in this space,” said Brian Sadler, Army senior research scientist for intelligent systems.

“I believe this is going to be a tactical offset strategy for the Army — the miniaturization of the robotics, the combination of large and small platforms, what it brings to the networking, what it brings to sensing and the ability to go fast in complex environments,” Sadler added.

Other MAST participants included University of New Mexico, Massachusetts Institute of Technology, Stanford University, Texas A&M University, University of California, Merced, University of Delaware, University of Texas, Austin, Kansas State University, University of Colorado, Bolder, Bowie State University and University of California, San Diego.

The Army plans to establish a new collaborative research alliance that will focus on distributed collaborative intelligent systems and technology.

A team of Oak Ridge National Laboratory researchers has received a three-year, $2 million contract from the Energy Department to study the potential use of machine learning tools in scientific data analysis.

ORNL said Friday it will explore deep learning methods to help scientists understand massive data sets through the Advances in Machine Learning to Improve Scientific Discovery at Exascale and Beyond project.

“This understanding can help scientists build and support new scientific theories, and help to design better materials,” said Thomas Potok, leader of ORNL’s computational data analytics group.

Potok will carry out the ASCEND project with fellow researchers Robert Patton, Chris Symons, Steven Young and Catherine Schuman.

The teams plans to use the Titan supercomputer at ORNL to test high-performance computing methods and build a deep learning network that will work to process and interpret data from multiple sources such as sensors.

A Battelle-University of Tennessee joint venture manages the laboratory for DOE.

The U.S. Army paired manned platforms with robotic systems on the ground as part of the manned-unmanned teaming demonstration held Tuesday at Fort Benning in Georgia, Defense News reported Friday.

The service branch’s Maneuver Center of Excellence combined a semiautonomous MRZR combat vehicle with an unmanned Hoverfly quadcopter to carry out reconnaissance operations as part of the exercise’s first scenario.

The Army also used a robotic wingman with a long range advance scout surveillance system – LRAS3 – to lead a group of crewed Humvees to detect positions of adversaries as well as a manned M113 armored personnel carrier to field a ground-based robot – Packbot – to conduct surveillance operations.

The robotic wingman fired at enemy targets after it received information from the manned Humvee.

The military branch also used the MRZR to perform reconnaissance, an Abrams tank section and a semiautonomous M58 vehicle with a smoke generator called Wolf as part of the Abrams Lethality Enabler demonstration.

The M58 Wolf vehicle works to conceal and allow the tank to move into its position by fielding heavy smoke.

The Army carried out the two-part demonstration in compliance with the Robotics and Autonomous Systems Strategy and Combat Vehicle Modernization Strategy.

Robert Sadowski, robotics chief with the Army’s tank automotive research, development and engineering center, said the service expects to transition the land-based robotic programs to the National Training Center within two to five years.