US Army
OEM : Defense
Assembly Line
Army Awards Palantir AI/ML Contract in Support of JADC2 Capabilities
Palantir Technologies Inc. today announced that the Army has awarded a new contract for up to three years to provide additional capabilities in support of the Combatant Commands (COCOMs), Armed Services, Intelligence Community, and Special Forces as they continue to test, utilize, and scale artificial intelligence (AI) and machine learning (ML) capabilities. The contract, posted to the Department of Defense contracting website last week, is worth up to $250 million through 2026.
Hybrid AI-Powered Computer Vision Combines Physics and Big Data
Many computer vision techniques infer properties of our physical world from images. Although images are formed through the physics of light and mechanics, computer vision techniques are typically data driven. This trend is mostly performance related: classical techniques from physics-based vision often score lower on metrics compared with modern deep learning. However, recent research, covered in this Perspective, has shown that physical models can be included as a constraint into data-driven pipelines. In doing so, one can combine the performance benefits of a data-driven method with advantages offered from a physics-based method, such as intepretability, falsifiability and generalizability. The aim of this Perspective is to provide an overview into specific approaches for integrating physical models into artificial intelligence pipelines, referred to as physics-based machine learning. We discuss technical approaches that range from modifications to the dataset, network design, loss functions, optimization and regularization schemes.
🖨️ Senvol to lead U.S. Army program focused on consistency of 3D printing performance
Senvol has announced that it has received funding from the U.S. Army to lead a program focused on demonstrating that consistent part performance can be achieved on different additive manufacturing machines located at different sites.
The program is titled “Applying Machine Learning to Ensure Consistency and Verification of Additive Manufacturing Machine and Part Performance Across Multiple Sites”, and commenced in March 2023, running through March 2025.
Aaron LaLonde, PhD, Technical Specialist – Additive Manufacturing at the U.S. Navy said “For additive manufacturing to be successfully implemented into the Army’s supply chain, it is essential to be able to produce parts of consistent performance even if different machines are used at different locations. Today, that is much easier said than done. During this program, we are pleased to work with Senvol to demonstrate the use of its machine learning technology to aid in achieving what everyone in the additive manufacturing industry strives for, a truly flexible supply chain.”
How a robotic arm could help the US Army lift artillery shells
To fire artillery faster, the US Army is turning to robotic arms. On December 1, Army Futures Command awarded a $1 million contract to Sarcos Technology and Robotics Corporation to test a robot system that can handle and move artillery rounds.
An automated system, using robot arms to fetch and ready artillery rounds, would function somewhat like a killer version of a vending machine arm. The human gunner could select the type of ammunition from internal stores, and then the robotic loader finds it, grabs it, and places it on a lift. Should the robot arm perform as expected in testing, it will eliminate a job that is all repetitive strain. The robot, lifting and loading ammunition, is now an autonomous machine, automating the dull and menial task of reading rounds to fire.
Inspection procedure with Manifest® augmented reality work instruction - US Army Abrams Tank
U.S. Army Awards Taqtile Phase II Contract To Expand Work Instruction Platform For Motor Pool
The recently completed Phase 1 program enabled the Army to validate Manifest’s unique capabilities to support digital transformation of motor pool MRO. Manifest demonstrably empowered personnel to complete complex tasks more safely, more efficiently, and more accurately than was possible with outdated paper-based processes.
“The nature of service in the Army results in a high amount of turnover in its motor pools as soldiers rotate through their assignments,” said Mr. Kelly Malone, chief customer officer, Taqtile. “The expanded use of Manifest with Army personnel will clearly demonstrate that we are uniquely capable of delivering knowledge right to operators and the equipment they’re working on, helping them perform like experts.”
U.S. Army’s New Expeditionary 3D Concrete Printer Can Go Anywhere, Build Anything
The U.S. Army Corps of Engineers’ Automated Construction of Expeditionary Structures (ACES) program is a game changer for construction in remote areas. The project will supply rugged 3D concrete printers that can go anywhere and print (almost) anything. The project started several years ago when concrete printers were very much in their infancy, but even then it was obvious that commercial products would not fit the Army’s needs.
ACES has produced multiple printers working with different industry partners. For example, ACES Lite was made in partnership with Caterpillar under a Cooperative Research and Development Agreement. It packs into a standard 20-foot shipping container and can be set-up or taken down in 45 minutes, has built-in jacks for quick leveling and can be calibrated in a matter of seconds, making it more straightforward than other devices. Overall the printer resembles a gantry crane, with a concrete pump, hose and a robotic nozzle which lays down precise layers.
The new technology is not magic, as 3D-printed construction is still construction. It does not do everything. A printed building still requires a roof and finishing touches like any other construction work. In areas with good logistics where equipment, labor and materials are all plentiful, there may be little advantage to the ACES approach. But in expeditionary environments, where all these things are likely to be in short supply, ACES could make a real difference.